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

Annotations already convey readOnlyHint, idempotentHint, and destructiveHint, so the bar is lower. The description adds valuable behavioral context: the 'counted once per borrower held' deduplication, the resolution of PE ids through the credit graph's cross-reference, and the handling of inference-based attribution ('A pair whose weakest basis is an inference is an inference'). This goes beyond what annotations provide.

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 and front-loaded with output metrics, but the opening sentence is a long run-on listing many fields with commas, making it harder to parse. It packs a lot of information into a few sentences, but a bulleted or more structured format would improve clarity without adding length.

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 must explain the return shape; it lists metrics but not their types, units, or how they relate to the parameters. It also omits semantics for 3 of the 4 parameters (sort, limit, min_borrowers). For a complex report tool with multiple configurable options, this leaves meaningful gaps for an agent trying to call it correctly.

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?

Only dfx_id receives meaningful description in the schema, but the tool description does mention it accepts 'a private credit sponsor id or a private equity id' and explains resolution. However, sort, limit, and min_borrowers have no description in either the schema or the tool description, and with only 25% schema coverage, the description fails to compensate for these undocumented parameters.

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 states the tool returns 'Sponsor by lender pairs counted once per borrower held' and lists the exact metrics (borrowers, facilities, principal, quarters, etc.), making the purpose clear. It does not explicitly distinguish itself from sibling tools like search_sponsor_lender, though the 'get' vs 'search' naming and the report-style output imply a distinct role.

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?

No guidance on when to choose this tool over alternatives such as search_sponsor_lender or search_sponsor_capital_providers. The description focuses on accepted inputs ('private credit sponsor id or a private equity id') and internal resolution, but never states the use case or exclusions, so an agent must infer when this report is appropriate.

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