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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true. The description adds behavioral value beyond annotations: it confirms no login/scraping/proxies required, hints at cost behavior ($0.02/call), and implies normalization (extracting fields). There is no contradiction with annotations. Slight gap: doesn't explain what happens if a company slug is invalid or an ATS provider fails, but the concurrency parameter and maxItems limit mitigate risk.

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 description is two sentences plus a pricing tag. Every word adds value: the first sentence states the action and output fields, the second clarifies the absence of login/scraping/proxies. The price and payment detail are front-loaded in the same concise block. No filler, no repetition of schema info.

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?

Given the tool's complexity (aggregator with varying ATS providers, concurrency settings, and normalized output), the description covers the core workflow, provider support, and cost. There is no output schema, so the description compensates by listing the output fields. It doesn't mention error handling (e.g., invalid slugs or rate limits), but the concurrency parameter and example prefills provide some guidance. Slight gap for full completeness.

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 100%. The description adds minimal parameter semantics beyond the schema, but the schema itself is rich: for 'items', it explains the 'provider:company' format with URL examples and allowed providers; for 'maxConcurrency', it gives defaults and bounds. The overall description normalizes the output fields but doesn't detail them in the parameter section—output schema is absent, so the description of normalized fields (title, location, etc.) partially compensates, earning a 4 instead of baseline 3.

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 explicitly states the tool pulls open roles from ATS systems (Greenhouse, Lever, Ashby) and normalizes them into structured rows. It distinguishes itself from siblings like 'xing-jobs' or 'computrabajo-jobs' by specifying the exact providers and the action of normalizing. The verb 'Pull' and resource 'open role from a company's public applicant-tracking system' are specific and clear.

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 clearly states when to use this tool ('Pull every open role from a company's public applicant-tracking system') and provides explicit capabilities ('No login, no scraping, no proxies.'). It implicitly sets expectations against alternatives by naming its provider scope, and the pricing note adds context for cost-sensitive selection. While it doesn't name specific sibling tools to avoid, the scope is well-defined enough.

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