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

With no annotations, the description carries the full burden. It discloses determinism, fixture-verification, guest rate-limiting, the option of using an api_key for higher limits, and the return of a Guild-signed provenance envelope. It also imposes a strict payload schema beyond the input schema, which is important behavioral context.

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?

The description is front-loaded with the primary purpose. Each subsequent section adds necessary detail: output characteristics, pricing/auth, and precise payload/output schemas. It is long but efficient; the embedded schemas replace what would otherwise be lengthy prose. No wasted sentences.

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?

The tool has a complex nested payload and an output schema. The description provides both schemas explicitly, explains the return value (result plus provenance envelope), and covers usage constraints (rate limits, api_key). It is complete enough for an agent to invoke the tool correctly without further context.

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?

The input schema provides no descriptions for api_key or payload (0% coverage). The description compensates fully: it explains the api_key's role in using a member budget, and it explicitly provides a restrictive JSON Schema for payload (example array, min/max items, additionalProperties false) that goes far beyond the loose 'object' type in the schema.

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?

The description opens with a clear, specific statement: 'Infer a JSON Schema from example instances.' It further details the exact behavior (draft-2020-12 schema, merging types, required keys, array item schemas), which distinguishes it from sibling tools like ag_json_validate or ag_json_diff.

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 use case is clearly implied: take example instances and produce a schema. It does not explicitly mention alternatives or when-not-to-use, but the description is unambiguous about its purpose. For a tool with many JSON siblings, explicit exclusions would be ideal, but the context is clear enough.

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