fact_check

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

With no annotations present, the description carries the full burden and discharges it well: it discloses the multi-step process, that internet access requires user permission, that it uses user preferences, that it is slow, and crucially that it writes nothing to the vault ('No guarda nada en el vault'). That side-effect disclosure is exactly the kind of context annotations would otherwise supply.

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 paragraph is long but dense and front-loaded with the core process, then the no-write guarantee, the latency warning, usage condition, and parameter note. Nearly every sentence earns its place, though the verdict-category enumeration is somewhat verbose given an output schema exists.

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 structure need not be explained, yet the description still covers behavior, side effects, latency, permissions, and the parameter switch. For a complex multi-step tool with no annotations, this is nearly complete; only the 'text' parameter's exact role is left implicit.

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%, so the description must compensate. It explains search_web clearly ('search_web=False: solo brain'), which is genuinely beyond the schema, but leaves 'text' undocumented (an agent must infer it is the claim to verify). Partial compensation for two parameters merits a 3.

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 states a specific verb and resource (verifies claims) and details the actual pipeline: separating claims, searching brain first, optionally searching the web, reading pages, grouping non-independent sources, and returning a rule-based verdict. This is clearly distinguishable from siblings like search_knowledge or read_url.

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?

It explicitly says when to use it ('cuando el usuario pida verificar algo o cuando haga falta comprobar un dato que no está en brain') and warns it is slow ('Tarda'). It does not name an alternative tool for the brain-only case, but the condition for use is unambiguous.

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