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

Annotations already declare destructive=true, idempotent=true, so the safety profile is known; the description goes further and discloses non-obvious consequences: removed keywords are retained as history and won't be regenerated, and the pool never falls below the minimum a run needs. These are behavioral facts 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 short, front-loaded sentences with no filler, leading with the action and the text-matching rule before the alternative and constraints. A few fragments ('Up to 25 per call.') are terse but each earns its place.

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 destructive, no-output-schema mutation tool, the description covers the action, matching semantics, the alternative route, history/pool side effects, and volume limits. Nothing an agent needs to invoke it 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 100%, so the schema documents both workspaceId and keywords; the description still adds value with the 'exact text as list_keywords shows it' matching rule and the 25-per-call limit, which is not encoded in the schema. Baseline 3 is exceeded by that extra constraint.

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 ('Stop discovery running these searches') rather than restating the name. It distinguishes itself from the sibling add_keywords by its inverse action and explicitly names plan_campaign_change as the tool for the adjacent case, so an agent can route without opening schemas.

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 concrete selection guidance: exact text as list_keywords shows it, and a clear alternative (plan_campaign_change) for the case of removing a whole kind of site. It also caps the call at 25 keywords, which tells the agent how to batch.

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