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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is covered upstream. The description adds value beyond that by disclosing the human-consent precondition and the downstream consequences ('Autopilot works from it once approved, and it is measured weekly'), though it never spells out what the destructive behavior actually replaces.

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 first sentence is a long expository definition of what a keyword map is rather than what the tool does, pushing the actual action verb into the second sentence. The final clause about weekly measurement is useful context, but the whole is not tightly front-loaded around 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 a one-parameter mutation with annotations and no output schema, the description covers preconditions and post-approval effects reasonably well. It omits what happens on failure (no draft present, already approved) and what the call returns, leaving gaps an agent must discover by trial.

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?

There is a single parameter with 100% schema coverage, and the schema already says 'Client name from list_clients'. The description contributes nothing about the client argument, so the baseline of 3 for high-coverage schemas applies.

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 and resource ('The agency approves the draft map (or the changes waiting for approval)'), so an agent knows this is an approval action on the keyword map. It distinguishes itself conceptually from save/get by emphasizing approval of an already-reviewed draft, but never names keyword_map_save or keyword_map_get, so the boundary with siblings is inferred rather than stated.

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?

Adds a real precondition: approval happens 'after the person has seen the clusters and target pages and said yes', which implies a human sign-off gate. However it gives no explicit when-not guidance (e.g. no draft exists, changes not yet reviewed) and never points to keyword_map_get or keyword_map_save as the alternative for viewing or editing the map.

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