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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description adds context beyond them: citation links are inline markdown, multi-article citations resolve to the first article with labelled links after the span, and absent `appellateFate` or `caseChronology` does not prove no recourse exists. These are substantive interpretive details an agent cannot infer from schema or annotations alone.

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 description is long but every sentence earns its place: it front-loads the core operation, then gives compact explanations of citation formatting, appellate fate, case chronology, absent-field caveats, and commentary contents. The structure is dense but purposeful, and no sentence is wasted or redundant with the schema.

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?

With one fully documented required parameter, read-only annotations, and an output schema present, the remaining risk is semantic misinterpretation of legal fields. The description addresses exactly that by explaining `appellateFate`, `caseChronology`, the open-world caveat for missing data, and what `commentaires` contains. An agent has enough context to call and interpret this tool 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?

The schema covers the only parameter fully, including its source (search_decisions hit or inline citation link) and its fallback guidance. The description reinforces "by its `url`" but adds little parameter-specific meaning beyond what the schema already provides; its rich detail is mostly about output-field semantics rather than the input parameter.

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 opens with a specific verb and resource: "Fetch the full text and metadata of a decision by its `url`." It differentiates from siblings by explaining how /texte/ links route to get_legal_text and /decision/ links route to get_decision, so an agent can distinguish this lookup tool from search_decisions and get_legal_text without ambiguity.

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 gives explicit when-to-use guidance: a decision URL should come from a search_decisions hit or an inline citation link, and if neither is available, the agent should call search_decisions first. It also tells the agent to read `appellateFate` before citing the decision as authority, which is a concrete usage rule.

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