record_extraction

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds the useful overwrite semantics ('re-recording replaces it'), telling the agent what gets destroyed, but says nothing about auth requirements, side effects on linked entities, or how relationships are reconciled.

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?

Two short, front-loaded sentences with no padding; the overwrite caveat is placed immediately after the core action. The guide("extraction") pointer is terse but earns its place.

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 6-required-parameter write tool with only 17% schema coverage, the description is too thin: it omits parameter provenance (run_id/uid/content_sha256), the maxItems caps on entities/relationships, and any hint of the replace-vs-append model beyond one parenthetical. It relies on the output schema and an external guide it never summarizes.

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 only 17%, so the description should compensate but adds nothing about parameters. It never explains run_id, uid, content_sha256, or page semantics, leaving the agent to infer provenance and identity requirements from field names alone.

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?

Specific verb+resource: 'Record the entities and relationships extracted from one page.' Clearly distinguishable from sibling recorders (record_screening_decisions, record_synthesis) by its one-page extraction scope. No explicit sibling differentiation is stated, but the resource is unambiguous.

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?

Points to the governing rules via guide("extraction") and warns that re-recording replaces prior data, which is genuine contextual guidance. However, it never states when this should be called versus alternatives, nor any preconditions (e.g. run must exist, page must be fetched).

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