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

Annotations already declare readOnly, idempotent, closed-world and non-destructive behavior, so the safety profile is covered. The description adds substantive semantics the annotations cannot: the no-keyword 'list everything' behavior, the filter-vs-field distinction, and what a field state object means (known vs Atlas-derived vs omitted vs extraction failed). It does not mention result count limits or pagination, which is the remaining gap.

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, front-loaded with purpose and followed by call shape, then the result vocabulary. No filler, though the parenthetical 'postings[].x is a posting property' is terse to the point of being slightly cryptic and the field-state sentence is dense.

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 a single optional parameter and no output schema, the description sensibly narrates what comes back (type plus short description, and the meaning of field state objects). That is nearly enough to call the tool correctly; only result limits and the relationship to search_docs are unaddressed.

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 meaning of 'keywords', and it does: it gives concrete example values and states the default semantic (empty array returns everything), which is not derivable from the bare array schema. It does not mention the 20-item cap or 100-character limit, but those are enforced by the schema itself.

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 opens with a specific verb and resource: 'Find search_jobs filters and job fields matching keywords.' It also ties the tool explicitly to the sibling search_jobs and states what each result carries (type and a short description), so an agent can distinguish this discovery tool from consumers like search_jobs, get_job, or count_jobs without opening a schema.

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 context is clear: pass keywords like ["pay", "remote"] to narrow, and 'no keywords lists everything' defines the empty-call case, while 'kind is filter or field' tells the agent how to interpret results before using them in search_jobs. It stops short of explicit exclusions, e.g. it never contrasts this with the sibling search_docs for looking things up, so the agent must infer that boundary.

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