Propose query clusters automatically

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

Annotations only declare the generic non-read-only/non-destructive profile, so the description carries real weight: it discloses that this is asynchronous background work, that it is non-mutating until apply_auto_clustering, that get_job must be polled, and that a subscription is required. It doesn't mention concurrency/rate behavior or what identifier the job returns.

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?

Dense but every sentence earns its place: scope, mode semantics, restriction flag, lifecycle warning, and prerequisite. The critical 'nothing changes until apply' constraint is front-loaded before the follow-up steps.

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 6-parameter async job-starter with no output schema, the description covers the modes, the non-mutating contract, and the poll/apply chain. It stops short of naming the return value (a job handle) that an agent must capture to poll get_job.

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 17% (requestId alone), but the description compensates by defining all three mode values and the restrictToExistingClusters semantics, plus the 500 cap on trackedQueryIds. organizationId and projectId are left to their self-evident names, which is acceptable.

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 ('start a background job that proposes how to group ... tracked queries into clusters') with the 500-query scope. It is clearly distinguishable from the sibling apply_auto_clustering, which is named as the downstream commit step.

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?

Enumerates the three mode behaviors, explains restrictToExistingClusters, and specifies the operational flow: nothing changes until apply_auto_clustering, poll get_job, show the proposal, then apply. Prerequisite (active subscription) is stated.

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