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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is covered. The description adds one genuinely new behavioral fact — that no analysis run is triggered — but omits irreversibility, whether associated data is purged, and permission requirements.

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?

Two short sentences with zero filler; the scope comes first and the behavioral caveat follows. Nothing is padded.

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?

This is a destructive, 4-required-parameter mutation with no output schema, yet the description never states what happens on success, whether removal is reversible, or how the project/prompt pair is scoped. Half the parameters are undocumented, so an agent lacks what it needs to call this confidently.

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 50%: context and llm_model are fully documented in the schema, but promptId and advertiserProjectId have no description anywhere. The description only implies promptId via 'one tracked ... prompt' and says nothing about advertiserProjectId scoping, so it fails to compensate for the gap.

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 ('Remove one tracked AI Visibility prompt'), and 'one' distinguishes it from bulk siblings. It doesn't explicitly name add-llm-prompt or delete-llm-monitoring as the alternatives, but the scope is unambiguous.

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?

'Does not start an analysis run' is a useful conditional hint about consequences, implying this is a cleanup action separate from create-llm-run. However, there is no explicit guidance on when to choose this over delete-llm-monitoring or how it relates to the add-* siblings.

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