jobs_fetch

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

With no annotations, the description carries the full burden. It usefully discloses partial-failure semantics ('a source can fail without stopping the others') and points at the `skipped` and `error` fields, which is real behavioral value. It omits that this is a write-heavy ingestion operation, its persistence behavior, and any rate-limit or auth considerations for the Apify source.

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?

Two tight sentences with the core action front-loaded and the error-handling caveat second. The reference to `skipped` and `error` is worth its space, though the backtick field names are unexplained without an 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?

For a multi-source, no-annotation, no-output-schema tool this covers the essentials of invocation plus a failure caveat. It still leaves the agent guessing about return shape, idempotency, and side effects on the job store, which matters for a fetch-and-write operation.

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 0% and neither boolean is described in the schema. The description indirectly maps to them via 'classify and score new jobs', so an agent can infer what score and classify toggle, but it never states that both default to true or what skipping them means for the output.

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 scope: run every job source (company boards, LinkedIn via Apify if configured), then classify and score new jobs. That clearly distinguishes it from siblings like jobs_search, jobs_list, and job_evaluate, though it does not name those alternatives 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: this is the full-refresh path that runs all sources and then classifies/scores. The parenthetical 'if configured' hints at a prerequisite for LinkedIn. However, it never says when to prefer jobs_search instead, whether it is safe to re-run, or what happens to already-fetched jobs.

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