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

Annotations only declare the safety profile (write, non-destructive, non-idempotent); the description adds the async background-job nature, the fact that nothing changes until apply_auto_clustering, the polling handoff to get_job, and the subscription prerequisite. That is meaningful context an agent cannot infer from structured fields.

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?

Four tight sentences, front-loaded with the action and scope, then modes, then the safety/workflow constraint. No filler or restatement of the title.

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 not be described; the description instead covers the async lifecycle, the mandatory apply step, and the subscription requirement. Nothing needed to invoke this tool 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 coverage is only 17% (just requestId), so the description carries most of the burden and largely delivers: it defines all three mode values, the effect of restrictToExistingClusters, and the 500-query cap on trackedQueryIds. It adds nothing for organizationId/projectId, hence not a 5.

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 ('start a background job that proposes how to group ... tracked queries into clusters') with the scope cap (up to 500). It is immediately distinguishable from the sibling apply_auto_clustering, which it explicitly references.

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?

Gives per-mode guidance for all three enum values (fill_gaps / add_on_top / full_regroup) and explains restrictToExistingClusters. It also spells out the required workflow — poll get_job, show the proposal, then call apply_auto_clustering — so the agent knows this is a staged, non-terminal step.

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