us-diligence

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses the concrete free-screen return shape (record count plus one sample record per source) and the failure behavior of unreachable sources being reported as 'not-checked' rather than 'clean'. This is meaningful context that prevents an agent from misreading an empty result as proof of no records.

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?

Two dense but efficient sentences pack in purpose, sources, use cases, return specifics, and failure semantics. The first sentence front-loads the core scoping ('US company', 'official federal records'); no word appears wasted.

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 single-parameter tool with no output schema, the description covers the applicable input (legal name), the sources, the use context, the output (counts and one sample per source), and the handling of unreachable sources. An agent can call this tool correctly and interpret the response correctly, with only minor unstated details like data freshness.

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%; the schema already defines 'name' as the legal name with an example. The description only restates that the tool screens a company name and contributes no additional guidance on formatting, normalization, partial matching, or required entity type. It meets the baseline but adds no surplus meaning.

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 opens with a specific verb and resource ('Due diligence on a US company, from official federal records') and then enumerates the exact screened sources: SEC EDGAR, OFAC SDN, USAspending.gov, and CourtListener/RECAP. It is immediately clear what the tool does and is not merely a restatement of the tool name.

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 explicitly lists four when-to-use decision points: onboarding a vendor, signing a supplier, screening a counterparty, or qualifying a sales lead. However, it does not state when not to use the tool or name alternatives; the free-screen limitation hints at when more than a sample is needed, but no explicit exclusions are provided.

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