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

With no annotations, the description carries the full burden and does so exceptionally: it discloses the 2-credit cost for the default 50 ideas, that every call is billed, that there is deliberately no offset/paging, and the critical trap that a full-length response is a cap rather than a complete result. It also explains the remedy (raise the row count in a single call up to the maximum), which is exactly the behavioral context an agent needs to avoid double-charging itself.

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?

The purpose and output shape are front-loaded, and the cost/cap guidance comes before the operational warning. The cap explanation is slightly redundant across three sentences ('no offset or paging', 'capped, not complete', 'raise the row count in a SINGLE call'), but each repetition is defensible given the billing consequences.

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 4-parameter read tool with no output schema, no annotations and no enums, the description supplies everything needed: returned fields, ordering, cost model, default size, cap behaviour, and the follow-up tool. An agent can call this correctly and interpret a full-length response without any external 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 description coverage is 100%, so the baseline is 3, but the description adds real meaning about the limit parameter: it is a hard cap, not a page, and it must be raised within one call rather than iterated. Country and language semantics (including the fallback to 'us') remain in the schema only, which keeps it below a 5.

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?

Specific verb+resource ('Returns related keywords around a seed term') plus the exact output fields (volume, difficulty, competition, intent) and sort order, so an agent knows precisely what comes back. It does not, however, distinguish itself from the sibling Bing_Keyword_Ideas, which appears to do a similar expansion job, so it falls short of a 5.

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 clear context ('Use it to decide what is worth covering') and names the natural follow-up tool, Keyword_Rankings, with the condition that selects it. It offers no exclusion or comparison against the Bing keyword siblings, so a 5 is not warranted.

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