get_publication

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

Annotations already declare readOnlyHint=true, so the description need not repeat safety. It adds useful context about what is fetched and the identifier format, but does not discuss not-found behavior, permissions, or response specifics. This is acceptable but not rich.

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?

Two short, front-loaded sentences: the purpose comes firstchen, then the argument explanation. No filler or redundancy.

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?

For a single-parameter read-only lookup tool with an output schema already present, the description is complete enough. It tells the agent what to pass and what outcome to expect.

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 0%, but the description compensates by naming the parameter and providing concrete valid formats ('hal-00001234' or 'tel-00987654'). This adds meaning beyond the bare schema, though not exhaustive.

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 uses a specific verb ('Récupère') and resource ('fiche détaillée d'une publication') plus a precise lookup key (HAL identifier), distinguishing it from sibling tools like search_publications or get_publication_stats. The example identifier formats further clarify the intended input.

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?

The usage context is clearly implied: use this when you already have a HAL ID and need the detailed record. It does not explicitly name alternatives or exclusion criteria, but given the one-parameter design and sibling names, the intended use is evident.

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