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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the useful operational trait that results come 30 per page starting at page 1, but says nothing about total counts, ordering, or what happens when the page is out of range.

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 sentences plus a pointer, front-loaded with what is listed and the pagination rule. No filler; the only slight loss is that the get_record pointer is tacked on without saying which case it serves.

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 two-parameter read tool with no output schema, the description covers the resource, the notable return field (response count), and pagination, and the annotations cover safety. The remaining gap is the undocumented 'q' filter, which an agent cannot infer from either the schema or the description.

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 burden. It explains the 'page' parameter well (30 items per page, numbering starts at 1), which adds real meaning beyond the bare integer schema. The 'q' parameter is left entirely unexplained in both schema and description, so the description only half compensates.

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 gives a specific verb and resource ('Lister les formulaires du projet') and adds a scope detail beyond the name: it also returns each form's response count. It partially differentiates from siblings by pointing to get_record(type: flows, id) for the definition, though it never contrasts itself with describe_forms or the various list_form_* siblings.

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?

It implies when to use it (when you need a paginated overview of project forms plus response counts) and explicitly routes to get_record(type: flows, id) for the full definition rather than here. However, it offers no exclusions against describe_forms, list_form_responses, or list_form_submissions, leaving the agent to guess which sibling to pick.

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