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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description adds the meaningful limitation that media attachments are only possible in the app, but it does not mention that repeated calls are non-idempotent (duplicate updates) or what authorization/ownership is required on the contract.

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?

A single front-loaded sentence that names the action first, then the payload, then the exclusion. No wasted wording, though the parenthetical example list and trailing app note make it slightly dense.

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 five-parameter create-style tool with no output schema and full annotation coverage, the definition covers purpose, payload shape, and the one workflow limitation an agent could otherwise get wrong. It lacks only return-value expectations and confirmation of whether the update is immediately visible, which is partly covered by proofs_public.

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 all five parameters are already documented. The description only marginally enriches this by giving example link types (YouTube video, Strava activity), which hints at what belongs in 'links'; it says nothing about content, week_start or proofs_public beyond 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?

The description gives a specific verb and resource ('Publier une mise à jour sur un contrat') and enumerates what an update is made of (text plus proof links). It does not name or differentiate itself from any sibling tool, but the action is unambiguous.

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?

Usage is implied rather than stated: publish an update with text and evidence links. The one genuinely useful constraint — that photos and voice notes must be attached from the app, not through this tool — is a real boundary, but there is no explicit when-to-use/when-not or alternative tool routing.

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