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

Beyond the readOnly/idempotent annotations, it discloses the important non-obvious behaviors: the tool is non-acting ('opens nothing by itself'), it emits procedural UI instructions, and the official API is not universally available. The odd future-dated check timestamp is noise, but the substantive behavior is covered.

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 core point is front-loaded, but the sentences are long and tangled—'Returns how to do it in JobAdder step by step ... and opens nothing by itself; then do it with...' is hard to parse. The trailing API/date sentence is awkwardly phrased and dated in the future, undermining trust.

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 no-param, no-output-schema guide tool, it explains the intended follow-up (browser tools) and the API fallback situation. It leaves unresolved how the candidate is specified and what exactly the step-by-step output contains, which matters for an agent deciding whether this alone answers the user's request.

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?

With zero parameters, the baseline applies; there is nothing schema-side to add. The description does not explain how the target candidate is identified (presumably via the browser session), which is a minor missed opportunity but not required given no params.

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 does state the deliverable—'Returns how to do it in JobAdder step by step (screens, buttons, fields)'—which clarifies that this is a how-to guide, not a data fetch. But the name 'get_candidate' and title imply retrieving a candidate record, and the description never reconciles that tension, nor distinguishes it from jobadder_search_candidates or other candidate tools.

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?

It gives partial workflow guidance: 'opens nothing by itself; then do it with the cotlet_browser_* tools in the user's JobAdder Cloud Browser,' which tells the agent this is step one of a two-step flow. It does not say when to call this instead of search_candidates or an API-backed read, and the API aside ('not for every account (checked 22 Oct 2026)') is suggestive but not an actionable selection rule.

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