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

Annotations already declare read-only, open-world, non-idempotent, non-destructive; the description adds real behavior beyond them: APIFY_TOKEN is required, Apify charges per job row plus once per run start while company rows are free, include_description carries no extra charge but slows Workday, board-mismatch rejection, and failures are returned as errors with a run ID. That is exactly the cost/permission/failure disclosure an agent needs before spending money.

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 purpose and format, and every later sentence (pricing, error/run ID, only_new) carries actionable information. The 17-platform enumeration and the long single-paragraph block make it denser than necessary, but it is not padded with filler.

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 14-parameter, zero-required, open-world scraping tool with no output schema, the description still covers return shape (per-job fields plus one free company row), partial-failure behavior, auth, and cost model. Nothing an agent needs to call it safely and correctly appears to be 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%, so all 14 parameters are already documented in the schema, including the domain/board-URL syntax and the equals-sign tie. The description mostly restates the filter set ('title, location, department, remote, and posting age') and only lightly clarifies only_new's state_key coupling; it never mentions max_charge_usd or max_jobs_per_company, so it adds little beyond structured data.

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: 'List every open job for a list of companies, read from their own applicant tracking system boards', then names the 17 supported ATS platforms. An agent knows exactly what this returns (job rows plus a company summary row) versus any generic job-search tool, and there are no siblings to confuse it with.

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 clear operating context: companies must be given as domains or board URLs, boards naming another employer are rejected, and state_key should be 'one key per schedule' for only_new runs. It does not state when to avoid the tool or what to do instead when a board cannot be found, so it stops short of explicit when-not guidance.

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