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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: PII masking with a concrete format (a**@example.com) and the exact permission (people.pii.read) required to see unmasked values. It does not cover pagination behavior or default result size, which is why this is a 4 rather than a 5.

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 tight sentences: capability first, then the masking caveat that determines whether results are usable. No restatement of the name or title, and the trailing clause about what masking signifies resolves the obvious follow-up question without extra prose.

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 an 8-parameter search tool with no output schema and 38% schema coverage, the description is missing result-shape hints, pagination semantics (cursor/limit interaction, max 100), and the environment default. It covers the highest-stakes behavior (masking/permissions) well but leaves enough gaps that an agent may need a trial call.

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 only 38% (only app and segment carry descriptions), so the description has to compensate. It does map meaning onto four parameters — q as free text, stage as lifecycle stage, tag, and segment — but leaves limit, cursor, and environment (including the production default) entirely undocumented in both places.

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 (Search) and resource (person profiles) and enumerates the four filter axes: free text, lifecycle stage, tag, saved segment. An agent can distinguish this from get_person (single-record fetch) by inference, but the description never names that sibling explicitly.

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?

Usage is implied by the listed filters rather than stated: there is no 'use this when...' guidance and no explicit pointer to get_person for a known id or to list_apps for resolving the required app parameter. Adequate but leaves routing decisions to inference.

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