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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond them: it discloses the hard 50-second server-side hold cap, the polling contract, the still_running flag, and the shape of a finished reply (output, pre-signed artifact links, note). This is exactly the behavioral context an agent needs to loop correctly instead of assuming one call suffices.

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?

Three sentences, front-loaded with the core action and then the loop rule and return shape; nothing is padding. The nested parentheses (range, per-kind ETAs) make it dense to scan but each fragment carries real information.

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 correctly takes on the return-value burden (output, pre-signed artifact links, note, still_running). It omits failure/expiry behavior — what a failed or expired job returns and what the agent should do then — which is the main remaining gap for a polling tool.

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 parameter meanings are already documented; the description nonetheless adds decision-relevant context by tying timeout_seconds to the submit reply's stated ETA and giving per-kind latency figures that drive that choice. The job_id-versus-task_id+kind relationship is left to the schema, which already states it, so this stays a modest add rather than a full re-explanation.

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 opens with a specific verb and resource: 'Wait for an async doseedo job to finish', then adds the mechanism (server-side polling) and the terminal outcomes (result or latest status). It implicitly separates itself from a one-shot status check by describing blocking/polling, but never names the sibling doseedo_check_task, so the distinction has to be inferred.

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 gives concrete operational guidance: if the reply has still_running:true, call again, and a submit reply's eta_seconds tells you how many calls a job needs, with per-kind examples (~15 s, 1–3 min, ~4 min). What is missing is routing guidance against alternatives — when to use this versus doseedo_check_task or doseedo_list_jobs if you do not want to block.

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