Lancer l'analyse sémantique d'un mot-clé

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

Annotations already mark this as a mutating, non-idempotent operation, and the description adds valuable async behavior: processing takes a few minutes and the caller must follow a task_id. This is useful context beyond the structured fields and does not contradict them.

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 a compact single sentence with the purpose front-loaded, followed by workflow and endpoint. It repeats the title's phrasing slightly but every segment adds information needed to invoke and monitor the operation.

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 an async operation with no output schema, the description explains the wait time and names the exact follow-up tools (getTask, getKeyword). It does not describe the launch response shape in detail, but the provided workflow is sufficient for correct invocation.

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 only 50% because id lacks a description. The description's endpoint clarifies that id refers to a keyword, and siteId is already documented as a hashid. It partially compensates for the gap but adds no format, constraint, or relationship details beyond the path.

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 starts with a specific verb ('Lancer') and resource ('analyse sémantique d'un mot-clé'), reinforced by the endpoint. It also distinguishes this tool from siblings by framing it as an async launch that requires follow-up via getTask and getKeyword.

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 description gives clear workflow guidance: launch the analysis, track the task_id with getTask, then read getKeyword. It does not explicitly state when-not to use the tool, but the sequential context with siblings is strong enough to orient an agent.

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