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

Goes well beyond the readOnly/non-destructive annotations by disclosing a refusal policy, the shape of the success envelope, the presence of refusal/error envelopes, and how to interpret LOW confidence with literal_only_result. These are exactly the behavioral traits an agent cannot infer from annotations or schema.

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?

Four dense sentences, front-loaded with purpose and scope, then the refusal rule, then the return envelope. Every sentence carries information, though the return-field list is somewhat compressed and slightly redundant with the output schema.

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 natural-language query tool with only two parameters, the description covers scope, acceptable question domains, refusal behavior, confidence interpretation, and output shape — the full set of things an agent needs before calling it.

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 semantics by spelling out what the free-text 'question' may express (industry, size, channel, ad format, cohort). It says nothing about conversation_id, leaving that to the schema.

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: reading cross-account cohort benchmarks from the Metadata analytics warehouse. The 'cross-account cohort' scope implicitly distinguishes it from the account-scoped sibling query_metadata_analytics_account, though the sibling is never named explicitly.

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 concrete guidance on acceptable questions (industry, size, channel, ad format, audience cohort) and explicit exclusions (named-company queries and identity-bearing outputs are refused). It stops short of naming an alternative tool for those refused cases, which keeps it below a 5.

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