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

Adds substantial context beyond annotations: the four possible verdicts, the itemized output shape, the epistemic caveat that 'could not verify' is not evidence of fraud, the immutability of each result ('checking again later produces a new one and leaves the first alone'), plus cost (25 credits) and latency (a few seconds). The immutability statement is consistent with idempotentHint=false and explains why readOnlyHint is false, so there is no contradiction.

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-loads the core purpose, then output format, then caveats, then use cases and cost — a logical order with no filler. It is on the long side, and the 'It will never tell you somebody is fake' passage spends several sentences on one point, but the content is substantive rather than padding.

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 carries the return-value burden and does so fully: the four verdict types, per-claim confirmation with source links, explicitly empty searches, and a list of what was never checked. Cost and turnaround are also covered, so an agent has everything needed to call and interpret it.

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 already 100%, so the baseline is 3, but the description adds real meaning: 'Paste whatever you have — the pitch email, a name, a link — and the claims are read out of it', clarifying that the free-text input is parsed rather than matched verbatim. It doesn't discuss how the optional name/title/employer overrides interact with extraction, leaving a small gap.

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: it 'checks those particular claims against the official lists that would record them', with concrete claim types (doctor, lawyer, broker, professor, director). An agent can immediately tell this is a credential-verification tool, distinct from siblings like enrich_person or get_dossier that assemble profiles rather than test claims.

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?

Gives explicit when-to-use triggers in quotes ('is this person who they say they are', 'check this expert before I quote them', 'is this doctor actually registered') and an implicit boundary via 'It will never tell you somebody is fake.' It does not name sibling tools as alternatives for adjacent needs, so it stops short of full routing guidance.

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