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

Annotations already establish readOnly/idempotent/non-destructive, so the description's real contribution is behavioral detail beyond them: a fixed page size of 25, result enrichment with per-job application counts and per-status-view totals, and the non-obvious exclusion of archived jobs from the 'all' view. It omits how paging is continued and any ordering default context, which are left to the schema.

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 tight sentences, front-loaded with what the tool returns and the page size, then the status vocabulary, then the one surprising rule about 'all'. No filler or restatement of the name.

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 an 8-optional-filter list tool with no output schema, it covers the most important unknowns: return shape, page size, and status semantics. Remaining gaps are minor, chiefly that pagination continuation via nextCursor is only in the schema and the default sort is unmentioned.

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 50%, with cursor, search, locationId and departmentId documented in-schema while sort, status, workMode and employmentType are bare enums (though self-explanatory). The description does add genuine meaning for the most ambiguous parameter by defining draft/open/closed/archived and clarifying that 'all' hides archived, but it says nothing about sort defaults or the filter semantics of workMode/employmentType.

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?

States a specific verb and resource ('Lists the company's jobs') and goes further by specifying what each row carries (application counts, with the 'new = inbox' definition). The job-vs-application resource split is clear enough to separate it from list_applications and get_job, though it never names those siblings explicitly.

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 rather than prescribed: it is evidently the paginated browse tool for jobs, and the 'all' view caveat steers filtering choices. There is no explicit 'use get_job for a single job' or 'use list_applications to see applicants' routing statement, so an agent must infer alternatives from the sibling names.

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