job_wait

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful non-obvious behavior — that a wait timeout does not cancel the underlying command — plus the default and range. It stops short of saying whether the call blocks, what it returns when the job finishes, or whether it returns immediately for an already-finished job.

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 with no filler, and the timeout bounds/default are front-loaded ahead of the non-cancellation caveat. Nothing is wasted.

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 simple two-parameter tool with no output schema, the description covers the timeout contract but leaves the core semantics thin: what constitutes a successful wait, what the caller gets back, and how this differs from job_status. Adequate to invoke, not adequate to use confidently in a polling loop.

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 description coverage is 0%, so the description must carry the parameter burden. It fully documents timeout (range 0–60, default 10), which is the non-obvious one, but says nothing about job_id despite it being the required parameter — its format and origin are left entirely to inference.

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 states a waiting action with a bounded timeout, but never says what is being waited on (job completion? status change?) — that is only inferable from the name and the job_id parameter. It also does not distinguish this from the sibling job_status, so an agent cannot tell from the text alone whether this blocks until done or merely polls once.

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?

There is no guidance on when to call this versus job_status or job_cancel, nor any stated prerequisite (e.g., call after starting a background job). The only conditional information is the timeout semantics, which is behavioral rather than usage-selection guidance.

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