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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes beyond them by disclosing the exclusion rules and the disconnected-channel case: a channel with canal_deconnecte = true is still listed read-only, readable but not sendable until reconnection. It also discloses the sort order (most recent contact signal first). Missing only return-shape or volume expectations.

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?

Four dense sentences that front-load the definition, then filter rules, then the disconnected-channel caveat, then ordering; each carries information. The opening fragment 'Données sans écran' is opaque and does not earn its place, slightly muddying the front-loading.

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 read-only list tool with no output schema, the description covers what qualifies, what is excluded, how results are ordered, and one notable output flag (canal_deconnecte). Pagination mechanics are left to the schema's cursor/limit fields, which is acceptable, leaving only minor gaps.

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 coverage is 100%, so the baseline is 3, but the description embeds silence_days in the definition ('n'ont plus donné signe depuis plus de silence_days jours'), clarifying the strict-inequality semantics that the schema ('Silence minimal en jours') leaves ambiguous. stage, limit and cursor are left entirely to the schema.

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?

States a precise verb (find) and a tightly defined resource: contacts who replied at least once, whose last inbound message was from the user, and who have been silent for more than silence_days days. This definition is specific enough that an agent can separate it from look-alike siblings such as laisses_en_vu or carte_relance without opening a schema.

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?

The scope rules (blacklist, groups, discarded follow-up stages, excluded or paused contacts) tell the agent what the list contains, and the reference to Ficiel's 'à relancer' selection gives context. However, no sibling is named and there is no explicit 'use this instead of X' or when-not-to-use guidance, so the usage decision is only implied.

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