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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds two useful traits beyond that: fact_id returns the fact along with its 'réserves' (caveats), and history_offset pages history in steps of ten. It still says nothing about result size, ordering, or the cryptic 'Aucun bulletin actuel déduit' constraint.

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 very short sentences with no filler, and the core purpose is front-loaded before the parameter notes. The telegraphic style costs some readability but nothing is wasted.

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 6-parameter tool with no output schema and zero schema documentation, the description should be more complete. It covers the three mode-selecting parameters but leaves q/limit/offset and the return-shape/pagination interaction between offset and history_offset unexplained.

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%, so the description carries the full burden and it does explain roughly half the parameters (fact_id, version, history_offset) with meaning beyond their types. The remaining parameters (q, limit, offset) are never mentioned, so an agent still cannot tell what q matches or how limit/offset interact with history_offset.

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?

Gives a specific verb+resource ('Rechercher les constats datés' — search dated findings), so the agent knows it is a search over a fact/finding corpus. However, it never distinguishes this tool from close siblings like search_information, search_research_sources or read_research_source, and 'constats' is left undefined.

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 description sketches three modes (fact_id to read one fact, version to read a revision, history_offset to page a revision's history), which hints at when each parameter matters. There is no explicit when-to-use/when-not or named alternative versus the many sibling search/read tools.

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