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

Annotations already declare read-only/idempotent, but the description adds material context beyond them: no credit charge, no provider lookup, limit values rounded down to 50/100/250, and critically that null metrics mean 'never fetched' rather than zero. It also warns that rows is only the current page while totalCount is the full match count.

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?

Front-loads what the tool does and the free/cached guarantee, then layers filters, pagination, null semantics, and result shape without a wasted sentence. Dense but every clause carries information an agent needs.

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 no output schema, the description carries the return-shape burden and does it well, naming the fields (totalCount, rows, metric values) and explaining their meaning. Combined with the cost and caching disclosure, an agent can call this correctly without further context.

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 baseline is 3, but the description adds real value: the rounding behavior for out-of-range limit values, the semantics of a null metric, and the totalCount-vs-rows distinction that the schema does not express. It does not restate defaults, which the schema already covers.

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+resource ("Lists keywords saved to a project") and scopes exactly what is returned: cached metrics plus tags. It is clearly distinguishable from save_keywords and research_keywords, which appear as siblings and are referenced by name.

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 strong context for when the tool is the right one: it is free, reads the local database, and runs no provider lookup. It also routes the agent to research_keywords when metrics are null. It stops short of an explicit when-not statement or broader alternative comparison (e.g. vs list_rank_tracking_keywords).

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