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

Annotations already declare readOnly, idempotent, non-open-world and non-destructive, so restating 'read-only, deterministic' is partly redundant. What genuinely adds value beyond the structured fields are the hard limits: 64 KB JSON input, 1 second per call, 1 MB result — constraints an agent cannot infer from the schema or annotations.

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?

Front-loaded and dense: purpose, when, when-not, side effects, determinism and limits each carry distinct information. Length is doubled by the ES/EN mirroring, which is intentional for a bilingual catalog but still inflates the payload for a two-parameter tool.

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 low-complexity extractor with an output schema already present, the description supplies everything an agent needs: extraction rules, exclusion of emails, the sibling alternative, and operational limits. Return-value shape is rightly left to the output schema.

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 100%, so both parameters are already documented, and the description adds no guidance on the `unique` flag (default true) — a real semantic gap since duplicate handling changes the output shape. The mention grammar does clarify what the `text` input is scanned for, but it is framed as extraction behavior rather than parameter semantics, so the 100%-coverage baseline of 3 holds.

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 a specific verb and resource (extract @mentions) and sharpens it with the grammar that defines a mention (letters, digits, underscore, dot; 1-50 chars) plus the negative rule that emails are excluded. It also names the nearest sibling (extract-hashtags), so an agent can distinguish it without opening any schema.

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?

Explicit 'When:' clause gives the selection condition (exact transform/compare/measure rather than approximation) and 'Not for:' names the alternative tool and its distinct task. This is the when/when-not/alternative pattern in full.

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