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 thoroughly: it discloses the return contents (observed vs. expected denial rate, coverage flags, method version), the free-preview vs. paid Evidence Brief distinction, the historical HMDA 2025 source restrictions, that this is not evidence of misconduct, and that it is not predictive of individual applications. This is well beyond a minimal 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?

The description is dense but not bloated; every sentence contributes either behavioral, licensing, or data-source context. It is reasonably front-loaded with purpose and returns. Minor stylistic noise like the leading 'ANSWERS:' and the attribution line could be trimmed, but the overall structure supports agent comprehension.

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?

Given there is no output schema and no annotations, the description supplies a strong amount of operational context: what is returned, data provenance, licensing limits, and interpretive caveats. It does not explicitly map the requested_format parameter to the free vs. paid distinction, and it does not contrast the tool with sibling screening/statistics tools, but the core invocation path is clear.

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 67%, and the description adds meaningful context beyond the schema: cohort_id is sourced from list_cohorts, and the full Evidence Brief requires a license a human must purchase. It also implies the free-preview/full-brief distinction relevant to requested_format, though it never names the parameter directly. The enum for requested_format is self-explanatory, and license_key's optional nature is in 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?

The description clearly identifies the tool's purpose: running a peer-adjusted screen on a cohort and answering queries like 'run the screen on <cohort>' and 'how do these lenders compare against expectation'. It names the resource (cohort) and the output (observed vs. expected denial rate), though it does not explicitly distinguish it from sibling tools like get_lender_denial_stats.

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?

The description gives usable context for when to invoke the tool by listing representative user queries and specifying that cohort_id comes from list_cohorts. It does not state when not to use it or name alternatives, but the trigger phrases provide clear selection guidance.

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