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

Annotations already mark this as destructive (destructiveHint: true) and not read-only (readOnlyHint: false). The description adds nuance by explaining that dismissal lasts until the next research run and that removing a cluster affects the normalization of remaining clusters, which are valuable behavioral details beyond the annotations.

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?

The description is concise, containing three sentences that each add value: state purpose, describe effects, and contrast with an alternative. No redundant information; structure is logical with a clear flow.

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?

Given there is no output schema, the description need not discuss return values. It covers the core functionality, side effects, and provides usage context. Minor omissions like error handling or prerequisites are not critical given the simplicity of the tool, but a brief note on required permissions or potential failure modes could enhance completeness.

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 0% with no parameter descriptions. The description explains the meaning of the 'status' parameter (dismissed vs. default) and implies the role of clusterId and projectId, but it does not explicitly define what these IDs represent or how they relate to each other. This leaves some ambiguity for the agent.

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?

The description clearly states the tool's function: dismiss or restore an opportunity cluster by setting status to 'dismissed' or 'default'. It also explains the specific effects on list_opportunities and create_content_plan_from_opportunities, distinguishing it from set_excluded_terms.

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?

Explicitly states when to use the tool (to dismiss or restore) and provides an alternative for a different use case (set_excluded_terms for durable 'not my product' signals). It also clarifies the temporary nature of dismissal, giving context for the tool's lifecycle.

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