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

Annotations give readOnlyHint and idempotentHint, but the description adds real behavior beyond them: the auth constraint ('seule la clé qui a passé la commande peut la suivre'), the expected latency (several hours), and the billing rule (failed/expired states are not billed). It does not discuss rate limiting for polling beyond 'de temps en temps', which keeps it short of a 5.

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?

One dense paragraph, front-loaded with purpose then parameter meaning then state semantics then polling advice. Every sentence carries information, though the parenthetical status list is compact and slightly run-on rather than crisply structured.

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?

With an output schema present, the description need not explain return values, yet it still summarizes the meaningful states and the auth/timing constraints an agent needs to poll correctly and interpret results. Nothing required for correct invocation is missing.

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 0%, so the description must carry parameter meaning and it does: run_id is defined as the identifier returned by run_service, which is the single most important thing an agent needs for this one required param. The status values enumerated are return-state semantics rather than parameter semantics, so they do not count here.

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 specific verb ('suivre') and resource ('commande asynchrone passée avec run_service'), and names the sibling run_service that creates the thing being followed. An agent can distinguish this from run_service (submit) and list_services (enumerate) without opening any 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?

Explicitly says when to use it (following a command created by run_service), how (poll 'de temps en temps', with the reason that work takes hours), and gives an exclusion: only the key that placed the command may follow it. That is when/when-not/alternative coverage.

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