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

With no annotations provided, the description carries the full burden. It discloses 'never throws on a missing path', 'deterministic', 'fixture-verified', 'free for guests (rate-limited)', and 'returns a Guild-signed provenance envelope'. It also specifies the exact payload schema, covering input constraints. Missing details about error behavior on invalid payloads, but overall transparent.

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 core action, followed by behavioral details and a mandatory JSON schema. Each section is purposeful; the embedded schema is essential despite making the description longer. Overall, it is well-structured and every sentence contributes value.

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 description includes the exact payload schema, which is critical given the vague input schema. It also mentions the provenance envelope and references the output schema (already provided externally). All necessary information for correct invocation is present, making the tool fully usable without additional lookups.

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 only defines payload as an object with additionalProperties true, which is highly generic. The description fully compensates by providing a strict JSON Schema for payload, complete with required 'value' and 'paths' array, minItems/maxItems, and additionalProperties false. It also explains api_key as optional for using a member budget, adding meaning beyond 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 uses the specific verb 'Extract' and clearly identifies the resource as a 'JSON value' with path syntax like 'items[0].name'. It distinguishes this tool from siblings (ag_json_diff, ag_json_validate, etc.) by focusing on path-based extraction and mentioning 'never throws' and 'stricter than asking a model to read a field'.

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 explicitly compares to an alternative ('Cheaper and stricter than asking a model to read a field'), which gives clear usage context. It also mentions rate-limiting and api_key for member budget, providing practical guidance on resource usage. It does not explicitly contrast with sibling JSON tools, but the purpose is distinctive enough.

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