Fetches new job postings, scores them, evaluates matches above a minimum score, and queues suitable roles for review without applying or sending anything.
Run the job agent once: fetch new postings, score them, evaluate the best max_evaluate new ones (score ≥ min_score)
and queue those worth applying to. Never applies or sends anything. Then call agent_queue.
| Name | Required | Description | Default |
|---|---|---|---|
| min_score | No | ||
| max_evaluate | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and it does disclose the critical trait that nothing is applied or sent. However, it omits other behaviors that matter for a multi-step job: that it writes entries into a queue (a side effect), whether repeated runs duplicate work, cost/latency of evaluating up to 15 postings, and what happens when zero postings clear the threshold.
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 short sentences, front-loaded with the verb and pipeline, followed immediately by the safety constraint and the required follow-up call. Every clause carries information; nothing is redundant or padded.
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 orchestrator with no output schema and no annotations, the definition should say what the agent gets back (counts of fetched/scored/evaluated/queued, or the queued items themselves) so the agent knows whether to inspect results before calling agent_queue. The pipeline and safety posture are well covered, but the return contract and side effects are not.
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%, so the description must compensate, and it does explain both parameters in context: `max_evaluate` caps how many of the best new postings are evaluated, and `min_score` is the score threshold for evaluation/queueing. It does not clarify ranges, whether `max_evaluate` also limits fetching, or the consequence of lowering `min_score`, and it leaves the defaults (65, 15) entirely to the schema.
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 names a specific operation ("Run the job agent once") and enumerates the exact pipeline stages it performs: fetch new postings, score them, evaluate the best `max_evaluate` above `min_score`, and queue the worthwhile ones. This clearly positions it as a one-shot orchestrator rather than the granular siblings (jobs_fetch, job_score, job_evaluate), so an agent can distinguish it 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?
It gives explicit sequencing guidance ("Then call agent_queue") and an important constraint ("Never applies or sends anything"), which tells the agent this is the safe non-committal path. It stops short of naming when NOT to use it — e.g. use job_evaluate for a single posting — so there is no explicit alternative routing beyond the follow-up call.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.