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

Annotations already declare readOnlyHint/ non-destructive/closed-world, so the safety profile is covered. The description adds genuinely non-structured facts: rows are paginated at 50 per page and each row carries columns plus JSON data, source, date, tags and status. It still omits sort defaults and total-count/next-page behavior.

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 what is returned, then paging, then the display hint. The telegraphic parenthetical list is dense but nothing is redundant; the French/English mix with the open_in_outil path is the only friction.

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 an 8-parameter, no-output-schema list tool with annotations present, the description covers returned content, page size, filters and a display path. It leaves a real gap around sibling selection (list_records vs this) and around sort/filter value conventions, so it is adequate rather than complete.

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 explanatory burden, and it does map most of the 8 parameters loosely to concepts: recherche (q), filtres (tag, source, statut), tri (sort, direction), and 50-ligne pages (page). It gives no syntax for sort field names, no default direction, and never explains the required id beyond the dashboard URL.

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 states a specific verb+resource ('Lire le tableau dynamique' with columns, JSON data, source, date, tags, statut) plus search/filter/sort behavior, so an agent knows it returns collection rows. It does not differentiate from near-siblings such as list_records or get_collection, which keeps it below 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?

There is an implicit usage hint: use this to read/filter/sort rows, and use open_in_outil with /dashboard/collections/<id> when the table must be displayed visually. There is no explicit when-not guidance and no mention of the alternatives (list_records, get_collection, export_collection_rows) that an agent should choose instead.

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