fact_check

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

No annotations exist, so the description carries the full burden and does so richly: it does NOT save to the vault, it is slow, it reads the user's Fact check preferences (nivel, actualidad, fuentes, buscador), and it discloses the full verdict taxonomy plus cites, dates, and limitations. This is exactly the behavioral context an agent needs before committing to a slow call.

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?

Dense but front-loaded: the process and what it produces come first, the slow-call warning and trigger follow. It is longer than ideal but nearly every clause (vault/no-save, verdicts, cites, FACT-CHECK.md pointer) adds distinct value, so little is wasted.

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?

An output schema exists, so return formatting needn't be explained, and the description already covers the verdict categories, cites, dates, and limitations it returns. For a multi-step tool with no annotations, this describes enough of the process, side effects, and rules reference (FACT-CHECK.md) to invoke it correctly.

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 0% with two params, so the description must compensate. It explains search_web's semantics precisely ('search_web=False: solo brain', defaulting to internet when permitted) and the required text param is self-evident. The one gap is that it doesn't state whether search_web requires prior user permission or is honored per-call.

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 (verifica afirmaciones) and a full process: separate claims, search brain first, then internet, read pages, group non-independent sources, rule-based verdict. The distinct process and the enumerated verdict scale let an agent tell it apart from generic search siblings without opening the 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 trigger: 'usala cuando el usuario pida verificar algo o cuando haga falta comprobar un dato que no está en brain', plus the when-not via 'search_web=False: solo brain'. It implies the brain-vs-internet routing but doesn't name the sibling search tool to use for plain lookups, so it stops short of full alternative routing.

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