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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description is consistent with a read of an external corpus. It genuinely adds behavior beyond that: the appended 'escrito del recurrente' can be over half the document, the operative reasoning sits under 'Réponse de la Cour' or 'Mais attendu que', and a ficha may arrive without text rather than as an empty decision. However, much of the length is citation etiquette for the agent's answer rather than properties of the tool call itself, so the behavioral payload is diluted.

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?

Purpose is front-loaded in the first sentence, which is correct. But the body is a stack of four ⚠️ blocks, two of them double-flagged, and a substantial share is post-retrieval citation policy (French verbatim first, marked working translation) rather than anything needed to select or invoke the tool. The emphasis markers multiply visually without adding decision-relevant 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?

There is no output schema, and the description compensates by naming the returned 'bloque_de_cita' with its header, template order, and link, plus the degradation case where no text is served. For a single-resource reader that is close to complete. What is missing is how it chains to the French search tool and what 'ventana' controls.

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% and the schema already documents 'modo' (with its enum glosses) and 'buscar' (mandatory in 'buscar' mode, in French). The description adds no meaning to 'modo', 'buscar', or 'ventana' – the window size is undocumented in both places, which is the main remaining gap. Baseline 3 applies since the schema carries most of the load.

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 opening sentence states a specific verb+resource: full text ('texto íntegro') of a French decision, and enumerates what comes with it (ECLI, visas, map of who speaks where). The jurisdiction word 'francesa' separates it from the many sibling 'leer_' tools for Colombia, Spain, Inter-American, etc. It stops short of naming the retrieval sibling (buscar_jurisprudencia_francia) that feeds it.

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?

Usage is only implied: the tool is the reader for French decisions, and the mode enum values are glossed in the schema, not in the description. There is no explicit 'call this after buscar_jurisprudencia_francia' or 'do not call for RD/Colombian material – use leer_sentencia_colombia' routing, which matters given roughly a dozen sibling readers. The Conseil d'État/Constitutionnel note gestures at an edge case but frames it as output behavior rather than a when-to-use condition.

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