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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds genuinely new behavioral facts: results are paginated by JSON Pointer with 'next' continuing the response, and reports retains failed measurements rather than discarding them. It does not say what happens when the name/version/contentHash triple is not found, but the pagination and history semantics are real added value.

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?

Three short sentences, front-loaded with the resource definition, with no filler. However, the terseness crosses into cryptic — terms like 'frontières' and 'contrôles' are never grounded in the section names the schema actually accepts, so density costs clarity.

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 7 parameters, 14% schema coverage and no output schema, the description carries a heavy load; it does well on return-shape concepts (sections, retained history, JSON-Pointer pagination) but omits how the required identity triple is formed and how limit/offset/sections interact with the pagination it describes. Adequate for the read-only safety story, incomplete for invocation correctness.

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 14% — only 'index' is documented, leaving name, version, contentHash, limit, offset and sections unexplained in the schema. The description only loosely gestures at this: 'publication exacte' hints the three required fields pick one artifact, and the listed sections (objet, interface, frontières, contrôles, performance) roughly mirror the sections enum, but it never explains required-field semantics, the 1-100 limit cap, or the section filtering behavior. It does not compensate for the coverage gap.

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 identifies a specific resource — the 'passeport' of one exact publication (name/version/contentHash, per the schema) — and enumerates what it contains: object, interface, frontières, contrôles, performance. It never states a verb and never distinguishes itself from nearby siblings such as law_editions, law_inspect or law_search, so an agent must infer that this is a retrieval tool for one pinpointed artifact.

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?

There is no statement of when to reach for this tool versus the ~20 siblings, and no prerequisites (e.g. that the publication must already exist). The only actionable hint is the sentence about the reports section retaining measurement history, which is content scope, not usage guidance.

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