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

Annotations already declare non-readOnly and non-destructive, and the description adds real behavior beyond them: names are lower-cased and must be unique, failures are reported per-name in 'failed' without aborting the batch, and retries are safe via requestId. It stops short of auth/permission or quota context, so 4 rather than 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?

Front-loaded with the action and scope, and the four sentences each carry distinct information (constraints, partial-failure behavior, follow-on tools, retry key). The names clause is dense, packing normalization, uniqueness and failure reporting into one sentence, but nothing is wasted.

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?

An output schema exists, so return values need no explanation, and the description still covers constraints, batch size, partial-failure semantics and idempotent retry. Nothing an agent needs to invoke this correctly 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 description coverage is only 25% (requestId only), so the description must compensate; it does so for 'names' by specifying the 100-item cap, lower-casing normalization and project-scoped uniqueness. organizationId and projectId remain unexplained in both schema and description, so it is not fully compensating.

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, resource and scope ('Create up to 100 query clusters in a project') and even defines what a cluster is ('the groups tracked queries are organized in'). An agent can distinguish it from rename_cluster, delete_cluster and list_clusters 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?

Names the follow-on tools explicitly ('Assign tracked queries with add_tracked_queries_to_clusters, or let start_auto_clustering propose groups'), which effectively routes the agent. However, it gives no when-not guidance, e.g. checking list_clusters first or using rename_cluster when the group already exists.

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