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

Beyond the read-only/idempotent annotations, the description discloses widget behavior: one card per contact, the fields displayed, the available buttons, and that 'Relancer' opens the follow-up card in the widget. It also explains an important edge case: a disconnected channel remains visible in read-only mode and cannot receive a prepared or sent follow-up until reconnected.

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?

The description is front-loaded with the core purpose and every sentence carries useful behavioral context. It is a dense single paragraph rather than structured bullets, but it does not waste space on repetition.

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?

Given the lack of an output schema, the description sufficiently explains what the widget shows: card fields, buttons, filtering behavior, selection rules, and disconnected-channel read-only behavior. Annotations and the fully described schema cover the remaining safety and parameter details.

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 100%, so the schema already documents all six parameters. The description reinforces `vus_seulement=true` semantics but does not add meaning beyond the schema for `stage`, `cursor`, `channel`, `account_id`, or `period_days`. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'AFFICHE UN WIDGET : la liste des contacts à relancer'. It explains the card contents and makes clear this is a display/list tool rather than the follow-up card or send action, distinguishing it from siblings such as ficiel_carte_relance and ficiel_envoyer_relance.

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 gives clear context for use: contacts to follow up, with `vus_seulement=true` narrowing to those who saw the last message without replying. It also lists selection exclusions, but it does not explicitly name when to choose this tool over sibling tools like ficiel_find_dormant_leads or ficiel_list_pending_cards.

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