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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond that: it reads through either API or browser, it preserves tables intact, and it deliberately does no searching. It still does not describe the shape or volume of what comes back, so it is useful 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?

Three short sentences, each carrying distinct information, with the read-first instruction placed early. The phrasing 'Outil conserve des tableaux' is slightly cryptic and could be tightened, but there is no filler.

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 zero-parameter, read-only, no-output-schema introspection tool, the description covers what it returns conceptually (sources, column models, limits, protocol) and what it does not do (searching). An agent has enough to decide to call it first before any collection work. Only the returned structure remains unstated.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The schema is empty and the description adds no parameter information, which is appropriate here.

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 names a specific verb (lire) and enumerates what is read: sources, column models, limits, and the collection protocol of MonAssocié, via API or browser. That is far more concrete than a bare 'describe' restatement. It stops short of explicitly contrasting itself with siblings like describe_resources, describe_forms, or list_collections, so it does not reach a 5.

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?

'Lire avant toute collecte' gives an explicit precondition for calling the tool, and the closing sentence clarifies a boundary: the tool does not perform searches, the agent must use its own authorized tools. That is clear usage context with a stated non-use case, though it names no concrete alternative tool.

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