Refresh one employer

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

Annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false) only sketch the profile; the description adds real behavioral detail beyond them: ~1 minute runtime, a 6-hour per-employer throttle, the exact throttled return shape (`refreshed: false`, `reason: "throttled"`, `last_refreshed_at`) with the note that no network request is made and it is not an error, plus the `known_not_indexed` case with its portal/reason/`employer_opt_in` fields. It also warns that every call hits a third-party endpoint.

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 action, then a bulleted rules block, then args and returns — a logical order with no wasted framing sentences. It runs long, and the parenthetical enumeration of non-indexed employers (Feishu-hosted, 蔚来 NIO, 毫末智行) is more detail than most calls need, but each bullet still carries an actionable rule.

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?

No output schema exists, and the description supplies the return contract itself (`refreshed`, `last_refreshed_at`/`next_allowed_at`, and jobs_new/jobs_updated/jobs_delisted/jobs_unchanged when it runs), along with the failure modes. An agent has everything needed to call it correctly and interpret the result.

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 description coverage is 0% and the lone `company` param carries no schema description, so the description must compensate — and it does: it accepts an id ("unitree") or any part of the name in either language ("宇树", "XPeng"), and ambiguous input is refused rather than guessed. That fully covers the only parameter's semantics.

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?

Opens with a specific verb+resource+scope: "Re-crawl ONE employer's public ATS now." It immediately distinguishes itself from siblings by contrasting the weekly index that makes `search_jobs` stale and leaving `check_watches` with nothing new, so an agent can route correctly without opening a schema.

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?

Explicit when-to-use ("the user is about to act on one employer and wants today's truth") and when-not-to-use ("Do NOT call this speculatively or in a loop... Search first"), with the alternative named. The single-employer constraint and the refusal behavior for vague input are spelled out rather than inferred.

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