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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that — that results carry a periodic freshness signal and a last-completed-check timestamp, and that not_available is not proof of closure — but says nothing about what happens with unknown or unavailable job_ids or how partial results are signaled.

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?

Three compact sentences with the read verb front-loaded and no filler. The wording is terse to the point of opacity in places ('selected details'), but every sentence carries meaningful information given the absent output schema.

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?

With no output schema, the description must explain the return payload, and it does partially cover the shape (details, freshness, last check time). However, for a two-parameter batch lookup it leaves the section-selection behavior and the job_ids constraints entirely unaddressed, so an agent still has to read the schema carefully to call it correctly.

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%, so the description must carry the burden for both parameters and largely fails. It never mentions job_ids (1–10 UUIDs) at all, and only the phrase 'selected details' loosely gestures at the sections enum (requirements, salary, evidence, verification) without naming any of its values.

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 says it 'Read[s] selected details, periodic vacancy freshness and the last completed check time', which conveys what kind of data comes back, but the resource is never named explicitly (only 'vacancy' appears), and it does not distinguish itself from the sibling search_jobs. An agent can infer this fetches job records by ID, but only from the tool name, not the description.

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?

There is no statement of when to use this versus search_jobs, nor any prerequisite about having job_ids in hand. The sentences 'Identity and applicant eligibility are separate checks' and 'not_available alone does not prove the employer closed the job' guide interpretation of results rather than tool selection, so routing guidance is absent.

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