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

Annotations already establish the safe read-only, idempotent profile, so the bar is lower. The description nonetheless adds genuine behavioral facts beyond them: literal keyword matching, AND semantics ('All words must match'), and normalization of PhD punctuation.

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 with the core scope front-loaded and matching semantics trailing. No filler, no repetition of the title.

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, five undocumented parameters, and an unexplained enum, the description leaves important gaps: what each surface searches, how job_id scopes results, and how limit/offset paginate. An agent could call it, but would be guessing at several inputs.

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 0%, so the description carries the full burden for five parameters. It adds meaning only for `search` (literal, all-words-match, punctuation-normalized) while `surface`, `job_id`, `limit`, and `offset` remain entirely unexplained in both schema and description.

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?

Specific verb (Search) plus resource (recruiting records) and explicit searchable fields (names, notes, activities, parsed résumés), which is clearer than most search tools. It does not, however, differentiate itself from the sibling yardstick_reporting_search, which is another search entry point.

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 scopes the data ('all authorized recruiting records') but gives no when-to-use guidance, no exclusions, and no pointer to alternatives such as people_list or reporting_search. The three-way `surface` enum (candidates/prospects/review) is never explained as choosing between search domains.

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