review_record

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

With no annotations, the description carries the full burden. It discloses that evidence requires a url and excerpt, that a 'full' review promotes a draft to reviewed, and the consequence of not recording first. These are behavioral traits beyond a simple 'record' action.

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?

Three sentences, front-loaded with purpose, then critical constraints. No fluff, each sentence adds essential information.

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 8 params, nested objects, and no output schema, the description covers the key edge cases: evidence provenance, promotion logic, and ordering. It gives enough context for correct invocation.

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 coverage is 75%, so baseline is 3. The description adds value by explaining evidence requirements (url+excerpt you actually read) and the effect of 'full' kind. This goes beyond the schema's per-field descriptions.

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?

States exactly what it does: 'Record a review against a hypothesis'. Specifies verb+resource, and adds context about format and side-effect (promotes to reviewed). Clearly distinct from siblings like 'hypothesis_record' which record hypotheses, not reviews.

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?

Provides clear context: use it when you have a review to record, and gives a critical ordering constraint ('Do not report a review to the user without recording it first'). Does not explicitly name alternatives, but the purpose is self-evident and the constraint is practical.

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