Add tracked queries to clusters

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

Annotations already declare non-destructive, idempotent, closed-world behavior, and the description still adds real value: the 100-item cap, additive (non-exclusive) membership semantics, and partial-failure handling where failures land in a 'failed' field without aborting the rest. 'Safe to retry' reinforces idempotency with operational meaning. It stops short of saying whether the whole call fails atomically or how the 'failed' entries are shaped.

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 short sentences, front-loaded with the core action and cap, then additive semantics, then failure behavior, then retry safety. No filler or repetition.

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 mutation tool with annotations covering safety and no output schema, the description covers scope, cap, additivity, partial failure, and retry safety – enough to invoke correctly. The main remaining gap is that no parameter is described at 0% schema coverage, so an agent must infer which ID goes where.

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 0%, so the description must carry parameter meaning, and it does not name or explain organizationId, projectId, trackedQueryIds, or queryClusterIds, nor their ID formats or the requirement that queries and clusters belong to the given project/organization. It only vaguely gestures at 'tracked queries' and 'query clusters' and never notes that the 100 cap applies to each array independently.

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 ('Add ... tracked queries to ... query clusters') plus the batch ceiling, so the operation is unambiguous. It does not explicitly contrast with the sibling remove_tracked_queries_from_clusters, leaving the agent to infer the inverse relationship from the name.

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?

There is no guidance on when to use this versus alternatives such as remove_tracked_queries_from_clusters, create_clusters, or apply_auto_clustering, nor any stated prerequisites (e.g. that clusters must already exist). The only usage-adjacent statement, 'Other cluster memberships are left alone,' describes effect rather than selection criteria.

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