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

Annotations only cover the read-only/idempotent safety profile, and the description adds substantive behavior: 30-credit cost on first lookup, zero cost on cached lookups, no charge on ambiguous-name or no-match outcomes, and candidate-return semantics for ambiguous names. This is exactly the cost/ambiguity context an agent cannot infer from schema or annotations.

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 payload description and use-case phrases before cost, which is the right order. Slightly bloated: the no-charge condition is restated three times ('nothing is charged ... nothing is charged when nobody matches') and the rhetorical 'the file, not the verdict' is decorative.

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 burden of explaining what comes back, and it does so at the section level (activity, collaborators, mentions, writings, news) plus the summary/full distinction via the schema. It stops short of depth/volume expectations, but nothing required to invoke correctly is missing.

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%, with every parameter self-documented (including the refresh charge note and the name/person_id either-or constraint), so the baseline is 3. The description adds little parameter-level detail beyond echoing the cost model already stated in the 'refresh' schema field.

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/resource ('everything on file about one person') and enumerates the returned sections—activity, collaborators, mentions, public statements, recent news. It also clears the field by naming what it is not ('this is the file, not the verdict') and what lighter siblings it competes with (brief, contact details).

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 concrete triggering utterances ('tell me everything about her', 'background on him before the call') plus explicit when-not guidance that routes to cheaper alternatives ('if you only need an email, ask for their contact details instead—that is far cheaper'; 'if a short written assessment is what you want, ask for a brief').

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