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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered; the description adds real value on top with the k-anonymity suppression rule (a cell appears only with 5+ outcomes or when you reported into it) and the provenance caveat that figures come from reported outcomes rather than predictions. That suppression rule materially changes how an agent must interpret sparse or empty results, which is exactly the kind of trait the schema cannot express. It stops short of 5 because it does not say what an empty response means versus a suppressed cell.

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?

Three tight sentences with zero waste: metrics first, dimensions second, the disclosure constraint third, then a one-line caveat. The k-anonymity rule is front-loaded before the agent could misread a missing cell as zero.

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 read-only, five-optional-parameter statistics tool with no output schema and no required arguments, the definition covers what is measured, how results are sliced, and why data may be withheld. Remaining gaps are how multiple filters combine and what an empty or suppressed result looks like, which are minor given the absence of an output schema.

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 only 40%, so the description has to compensate: program_id, institution and reporter_key are undocumented in the schema. The description names program, institution, industry and state, giving meaningful mapping for four of five parameters, but it never clarifies whether these act as filters or as group-by axes, and it omits reporter_key entirely despite that being the key that unlocks small cells.

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?

Names the exact metrics returned (approval rate, funded rate, median days to decision) and the grouping dimensions (program, institution, industry, state), which distinguishes it from siblings like report_outcome or find_lenders. It never explicitly names an alternative, so it falls short of the top band, but the resource and output are unambiguous.

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?

"From reported outcomes" and "counts of decisions, not predictions" imply this is the aggregate/retrospective view rather than a forecasting or lookup tool, which nudges the agent away from next_best_option. However, there is no explicit when-to-use or when-not-to-use statement and no routing to find_lenders, industry_overview or lender_program, leaving the choice to inference.

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