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

Annotations already declare read-only, idempotent, non-destructive and closed-world, and the description still adds substantive behavior: a 250-job result ceiling, page sizes of 50 (10 when descriptions is "full"), cursor-based paging via next_cursor, the default compact summary field set, and the snippet-vs-full tradeoff. These are operational constraints an agent cannot infer from the annotations.

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?

Front-loaded with purpose and then ordered by what an agent needs next: filter discovery, paging, result caps, output shape, then matching semantics. It is dense and somewhat run-on, but nearly every sentence carries a distinct constraint and none is filler.

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 tool with 7 top-level parameters and ~50 nested filters and no output schema, the description covers paging, caps, defaults, result shape and fallback tools well enough to call it correctly. The remaining gap is that most individual filter keys are left to list_fields rather than described inline.

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 coverage is 71%, and the description adds real meaning on top: comma-separated or array acceptance for country and employment_type, the phrase-in-order semantics of title versus AND/OR/NOT for title_advanced, the allowed sort values, and the limit defaults per mode. It does not explain the many $ref'd filters that carry no schema description (msa, stale, active, has_pay, source_class, etc.), though it does redirect to list_fields for those names.

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?

Opens with a specific verb and resource plus the facet list it searches ('keyword, title, company, place, pay and date'), and names siblings (list_fields, count_jobs, get_job) so an agent can separate this from them without opening any 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?

Explicit routing is given at several decision points: list_fields for filter names, count_jobs when the agent only needs match volume, get_job or view/fields when more detail is needed, and title_advanced when boolean word matching is required instead of phrase matching. It also states the escalation path when results are truncated ('narrow filters or use count_jobs').

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