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

Goes well beyond the readOnly/idempotent/non-destructive annotations: discloses that the PDF is fetched live from oig.hhs.gov, that text is extracted, and crucially that a missing PDF returns found:false rather than an error — a non-obvious failure mode an agent would otherwise misread as a tool failure. Also notes the source is keyless HHS-OIG.

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?

Front-loaded with the core question the tool answers, then the mechanics, then caveats. The obligation-category enumeration and the two caveat clauses are long but each carries decision-relevant information. Mild redundancy between 'reports which of those obligation categories appear in the text' and the earlier question framing.

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 still conveys return semantics: per-category presence plus a short excerpt, and found:false for entities lacking a posted PDF. Together with the sourcing and keyless note, an agent has enough to call it and interpret results without guessing.

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 both parameters are already documented, including that document_url overrides name lookup. The description restates that precedence and adds only the provenance hint (agreement_url from oig_cia_check), which the schema already implies. Baseline 3 applies since the schema does the heavy lifting.

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: fetch a named entity's Corporate Integrity Agreement PDF and report which obligation categories (Board Resolution, IRO reviews, Compliance Officer, reporting, disclosure program, excluded-persons screening) appear in its text. The enumerated categories and the 'this entity's ... actual' framing distinguish it sharply from oig_cia_check (which finds agreements) and oig_cia_list.

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?

Makes the chaining explicit: it resolves the entity the same way as oig_cia_check, or accepts a document_url taken from oig_cia_check's agreement_url field. It also sets expectations for when a category will be absent (sole-individual CIAs, older agreements with no posted PDF). It stops short of an explicit 'call oig_cia_check first if you don't know the entity,' leaving that step inferred.

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