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

Despite annotations already covering the safety profile, the description adds substantial behavioral context beyond them: the 30-minute freshness window, oldest-first ordering, per-minute/hour/day rate limits, the filters_too_broad rejection, and that over-limit jobs are dropped permanently (skipped_count). It doesn't explain cursor invalidation or quota-exhaustion behavior, but the disclosure is well above the annotation baseline.

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 source selection, then rules and limits, all of which earn their place. It is dense but not padded; the only cost is length, which is justified by the number of enforced constraints.

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 compensates by specifying the return format (short cards with title, description, skills, type, budget/rate, client country), ordering, and freshness. Missing pieces an agent would need — auth and error semantics — are minor against the enforced-limit disclosure.

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 high (83%), so the baseline is 3; the description still adds real meaning by explaining the mutually exclusive source parameters, that cursor must be passed back from the previous response, and that lookback only applies to filters without a cursor. It does not document the nested filter grammar in depth, but the schema carries that.

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+resource ('Find new Upwork jobs') and explicitly scopes itself as 'the tool for job search and monitoring', which separates it from siblings like get_job_details and list_feeds. The three mutually exclusive sources are named inline, so an agent can route correctly without opening the 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?

Gives explicit source selection (feed_id / all_feeds / filters) with filters as the default, then a numbered workflow: put every user criterion into filters, then judge returned jobs, then call get_job_details only for the few worth showing. It also names the constraint (ask the user for filters first, never request broad sets) and the fallback tool for detail.

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