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

Annotations already mark read-only/idempotent; the description goes further by disclosing that the map reflects the last refresh and is empty until GSC history exists, plus the cost implication of no AI credits. This is genuine added context beyond structured metadata.

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?

Every sentence carries unique information: definition, freshness, alternative, scoping, cost. It is not overly long and the core purpose is front-loaded, though the cost sentence could be seen as extra but is ultimately useful.

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?

With an output schema present and a single enum action, the description covers the essential runtime behavior (cached, pre-scoped, free) and routes to keyword_research when freshness matters. Nothing an agent needs to invoke it correctly is unresolved.

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% for both parameters, so the baseline is 3. The description adds the important clarification that no domain or site parameter is needed, which prevents an agent from trying to pass workspace-scoping arguments; the action enum and optional user_intent are otherwise fully self-explanatory.

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 the exact resource ('cached keyword-cluster map') and its content types, and contrasts with keyword_research for live numbers. The tool name and schema action 'list' align, so an agent knows it is a lookup of the precomputed map.

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 tool for live demand ('use keyword_research') and explains the cached nature, telling the agent when to pick this over a recomputation. Also clarifies that the tool is pre-scoped and requires no domain/site parameter, removing a common invocation uncertainty.

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