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

Annotations already declare destructiveHint=true and readOnlyHint=false, so irreversibility is signalled structurally. The description adds real behavioral context beyond that: the operation is blocked while an analysis run is in progress, which is a precondition an agent cannot learn from the schema. It does not say whether historical monitoring data is retained or whether the block is retryable, so it falls short of full disclosure.

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 short sentences with zero filler: action and scope first, precondition second, alternative last. The most important routing information is front-loaded.

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, three-parameter mutation with no output schema, the description covers scope, a blocking precondition, and the sibling alternative. The main remaining gap is the fate of existing monitoring results after deletion, which an agent might need to warn the user about.

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 100%, and each parameter already carries detailed inline guidance (including the context and llm_model conventions), so the schema does the heavy lifting. The description adds no meaning about advertiserProjectId or llm_model. Baseline 3 applies.

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 ("Delete AI Visibility monitoring") scoped to "a project", which distinguishes it from the per-prompt sibling. An agent can immediately tell this removes monitoring at the project level rather than a single prompt.

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 names the alternative and the condition that selects it: "Use remove-llm-prompt to remove one prompt." It also flags a blocking state (analysis run in progress) that gates use. It stops short of saying when a full project-level removal is warranted versus disabling monitoring, but the routing guidance is clear.

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