Create query clusters

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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) by disclosing non-obvious write semantics: names are stored lower-cased, must be unique per project, and any name that fails is reported in 'failed' without aborting the remaining creations. It also explains the idempotency-key retry contract, which annotations alone cannot convey.

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?

Three dense sentences, front-loaded with the core action and scope, followed by behavioral constraints and routing/retry guidance. No filler, though the sentence on name storage and failure handling packs several distinct facts together.

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?

With no output schema, the description usefully explains the partial-failure return shape ('failed') and the requestId retry contract for this mutation. It omits permission/auth prerequisites and what a successful response contains, but otherwise covers what an agent needs to invoke it correctly.

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% (only requestId is documented in-schema, and the description echoes the retry guidance rather than adding syntax). The description does add real meaning for 'names' (normalization, uniqueness, partial-failure behavior) and confirms the 100-item cap, but organizationId and projectId remain undocumented in both places.

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 ('Create up to 100 query clusters in a project') plus a definition of what a cluster is, and the scope constraints (max 100, unique lower-cased names). It is clearly distinguishable from siblings like start_auto_clustering and set_tracked_query_clusters, which are named explicitly.

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 two adjacent alternatives and their purposes ('Assign tracked queries with set_tracked_query_clusters, or let start_auto_clustering propose groups'), plus the retry protocol with requestId. It gives clear context for choosing this tool, though it doesn't state explicit exclusions (e.g., when not to create clusters manually).

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