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

With no annotations at all, the description carries the full burden: it does disclose the complete state machine and that the response includes usage, error, and result payloads, plus an expected polling interval that implies rate expectations. It omits what happens for an unknown or expired job_id, how long results are retained, and whether the call is safe/non-mutating (only implied by the name).

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 what is returned and followed by the operational polling rule. No filler, no restatement of the tool name.

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 single-parameter polling tool with no output schema, the return values and polling cadence are adequately covered. However, with zero annotations and zero schema descriptions, the definition leaves gaps on error behavior for invalid/expired job ids and on where the job_id comes from, which matter for correct invocation.

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% for the single required job_id parameter, and the description adds no meaning about its format, origin (presumably from start_embedding_job), or validity rules. The parameter is guessable, but nothing in the text compensates for the missing schema documentation.

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 enumerates exactly what is returned: status, usage, error or result, plus the full state vocabulary (queued, running, succeeded, failed, cancelled, expired). That is concrete and lets an agent know this is a poll-for-status tool rather than a job starter or result fetcher, though it never explicitly contrasts itself with siblings like start_embedding_job or get_result_url.

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?

"Poll every 5 s while queued or running" is real, actionable usage guidance that tells the agent both the cadence and the condition under which polling should continue, and implicitly when to stop (the listed terminal states). It stops short of stating when-not to use it or naming an alternative tool for retrieving finished output by URL.

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