Job status

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses mechanics an agent could not otherwise guess: wait_ms long-polls inside this server rather than holding a request open on the node, every response reports who holds the shared model and the wait queue depth, and results include what the model learned and did not. It also covers the recovery path when the job_id was lost by accepting a node lesson id.

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?

Four sentences, front-loaded with what is returned, then the wait_ms mechanic, then the response contents, then the id fallback. Each sentence carries distinct information, though the first sentence is long and its em-dash clause makes the core statement harder to parse than necessary.

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 only two parameters and no output schema, the description carries the return-value burden itself and does so: it describes the landing result, lesson-level learning detail, model ownership and queue depth. It stops short of enumerating the possible job states or what happens when job_id is unknown or expired, which an agent polling for completion would benefit from.

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 100%, so the schema already defines both fields, but the description earns above baseline by explaining why wait_ms exists (server-side long-poll converting a poll loop into one call) and why job_id tolerates a node lesson id (a conversation that lost its job_id is not stuck). It adds rationale rather than repeating types.

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 the resource (a job) and the question it answers ("where ... has got to, and its result once it lands"), and enumerates the producing tools (live_test, teach, teach_preflight, apply_knowledge, remove_knowledge, buy), which sharply bounds what a job is. It does not distinguish itself from job_list or node_status, so an agent must infer the split from names alone.

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 context is explicit: call this for a job previously started by one of the listed tools, and use wait_ms instead of writing a poll loop ("turning a poll loop into one call"). There is no exclusion guidance — nothing says when to prefer job_list or node_status, or what to do if the job id is unknown entirely.

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