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

With no annotations, the description carries the full behavioral burden and does well: it discloses the underlying data provenance (seven ATS platforms), crawl cadence (twice daily), the time windows of the trend calculations, and — critically for an autonomous agent — the price and payment rail ($0.01 USDC on Base via x402). It also implicitly describes the return shape via the metric list since there is no output schema. It does not say what happens when a company has no detectable ATS board or how history depth is bounded, which is why it is not 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?

The motivating question is front-loaded, followed by data provenance and then the metric list, ending with the price disclosure — a sensible priority order. It is a single dense sentence with a long parenthetical enumeration of ATS providers, which is slightly list-heavy but every element (source, cadence, metrics, cost) is decision-relevant, so little is wasted.

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 a one-parameter read tool with no output schema and no annotations, the description supplies what an agent actually needs: what is measured, over what windows, from what sources, how fresh, and what it costs. The remaining gap is failure/coverage behavior for companies not tracked by any supported ATS, which matters for a paid call but is a minor omission overall.

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?

There is a single parameter at 100% schema description coverage, and the schema already specifies accepted forms (name, domain, or careers-page URL) with concrete examples. The description adds nothing about input format or ambiguity resolution such as duplicate company names or unsupported ATS hosts. Baseline 3 applies when the schema does the heavy lifting.

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?

The description opens with a concrete question ('Is a company growing or cutting?') and then names the specific resource: posting-level history from named ATS providers (Greenhouse, Lever, Ashby, etc.) crawled twice daily. The metrics enumerated — open roles, adds/removes per week, net change, growth rate over 7/30 days, team and location breakdowns — make the deliverable unambiguous. It stops short of explicitly distinguishing itself from siblings like company_jobs or jobs_search, which is the only thing keeping it from a 5.

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 framing question — an agent can infer this is for headcount momentum questions rather than current open-role lookups. However, there is no explicit statement of when to prefer this over company_jobs, jobs_new, or jobs_search, and no stated exclusions. The guidance is inferable but not supplied.

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