ag_json_schema_infer

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With zero annotations, the description carries the full behavioral burden and largely meets it: it discloses determinism, fixture verification, guest free-tier with rate limiting, the api_key member-budget path, and the Guild-signed provenance envelope in the return. It also states the payload MUST match a given schema, flagging a hard validation constraint. It doesn't address error behavior or what happens on schema mismatch, a modest gap for an inference tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Information-dense and front-loaded with the core purpose, but it embeds two full JSON schemas verbatim, which inflates length considerably. The embedded schemas are arguably necessary given 0% schema coverage, but the provenance-envelope and budget details could be tighter. Every sentence earns its place, yet the density is at the edge of what an agent can parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations and low schema coverage, the description covers input constraints, determinism, auth/budget, and the signed-envelope return, and the output schema is provided separately. Missing only error semantics and a concise example, which keeps it from a 5. The agent has enough to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does: it embeds the full payload contract (examples array, 1-100 items, required, additionalProperties false) and explains the api_key parameter's role in rate-limit/budget terms. The raw input schema shows payload with additionalProperties: true, so the description's stricter 'MUST match' schema adds critical meaning the schema alone does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ('Infer a JSON Schema from example instances') and immediately disambiguates from the sibling cluster (ag_json_repair, ag_json_validate, ag_json_diff) by stating it produces a draft-2020-12 schema. It specifies exact generalization mechanics (merged types, required keys present in all examples, array item schemas), leaving no doubt about what the tool does or how it differs from its siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the input contract (payload must match a schema with examples array, min 1, max 100) and the output shape, which effectively defines when it applies. It doesn't name alternative tools for when NOT to use it, but the purpose is distinct enough that a sibling is never a plausible substitute. Minor gap: no explicit 'use this instead of validate/repair' routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.