Agent Tool Schema Intelligence API
Check caller-supplied tool definitions, JSON Schema, and OpenAPI documents for shapes, names, overlaps, examples, required fields, dialect keywords, size, and description gaps that make an agent pick or call a tool incorrectly.
Find malformed JSON Schema and OpenAPI tool definitions in caller-supplied tools: bad types, required names that are not properties, empty enums, and duplicate tool names. Nothing is fetched.
Flag generic tool names, generic parameter names, and descriptions that repeat the name or are missing. Matching is against a fixed word list, not a language model.
Compare caller-supplied tools for the same name, the same description text, or a very high overlap of longer words. Sharing a few keywords is not treated as a duplicate.
Check caller-supplied request examples against their JSON Schema types, required fields, enums, and bounds. External schema URLs are not fetched.
Find required names that are not properties, repeated required names, and required fields that also declare a default. The audit uses only the supplied schema.
Report JSON Schema keywords that the caller-selected dialect does not allow. Targets are draft-07, 2020-12, OpenAPI 3.0, and OpenAPI 3.1. The schema is not sent to a validator service.
Estimate tokens for caller-supplied tool names, descriptions, and schemas at four characters per token. The figure is an estimate, not a provider tokenizer count.
Score whether a tool description states a purpose, inputs, outputs, and when to use it. The checks are phrase and length rules, not a language-model reading.