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

The annotations already declare readOnly/idempotent/non-destructive, so the description correctly spends its words on the long-poll mechanics the annotations can't convey: the hard 50 s server-side cap, the still_running flag contract, and what a finished job returns (output, pre-signed artifact links, note). It does not say what happens on job failure, cancellation, or timeout expiry with no result, which is the main behavioral gap.

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?

Front-loaded with the action and the cap, then the retry rule, then the return shape — a logical order with no filler sentences. The parenthetical duration lists for transcribe/render/audio_to_session are useful but dense enough that the sentence becomes slightly hard to scan.

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 no output schema, the description carries the return contract itself and does so (output, artifacts, note, still_running), plus the polling cap and retry pattern — enough to invoke it correctly. Failure modes and the check_task alternative are the notable omissions for a tool in a family with cancel_job and check_task siblings.

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 100%, so the baseline is 3. The description restates timeout_seconds' 5–50 bound and the 'call it again' loop, and the schema itself documents the job_id-replaces-task_id+kind relationship; the description adds no new parameter meaning beyond that.

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 specific verb and resource ('Wait for an async doseedo job to finish') plus the mechanism (server-side polling) and the return contract (result or latest status). It is clearly distinguishable from submit tools, but it never names the near-identical sibling doseedo_check_task, so the agent must infer the wait-vs-poll distinction itself.

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?

Strong guidance on the repeat-call pattern: 'If it returns still_running:true, call it again,' with eta_seconds from the submit reply as the budgeting heuristic and concrete duration examples. What is missing is the exclusion case — when to use doseedo_check_task instead, or how this interacts with doseedo_cancel_job.

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