jobs

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

With no annotations the description carries the burden, and it delivers real behavioral facts: jobs outlive the server and the conversation, the registry lives at ~/.sima/jobs or SIMA_JOBS_HOME, and each job's folder (sima_jobs/<id>/) holds the engine files and result. What's missing is an explicit statement that this call is a side-effect-free read.

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?

The scope and ordering are front-loaded, which is good, but the final sentence about per-job folders and storage layout drifts from listing behavior into filesystem trivia. It is informative but partially tangential for a list tool whose output schema already covers the return shape.

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?

An output schema exists, so field-by-field return values are not required, yet the description still names the fields and the sort order. Combining that with persistence semantics and the registry location makes it nearly complete; only the read-only nature and the `name` matching rule are unstated.

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% for the single `name` parameter, so the description must compensate — and it does, explaining that `name` keeps only one session's jobs rather than all. It stops short of stating whether it matches a session name, a job id, or a label, which leaves real ambiguity.

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 clearly establishes the resource and scope: every job sima knows on this machine, including the registry location, and enumerates the returned fields (id, tool, status, label, progress) with ordering (running/queued first). It falls short of a 5 because it never names or contrasts with the obvious siblings job_status, job_result, and job_cancel, so the agent must infer the difference.

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 does say what the `name` parameter narrows to (one session's jobs), which implies the usage pattern, and it implies this is the broad listing tool. But there is no explicit when-to-use/when-not guidance and no routing to job_status or job_result, so the agent has to infer the split from sibling names alone.

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