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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds what actually comes back: status plus, on completion, pre-signed file links and a conversion transfer report with named fields. It also flags that job_id alone is sufficient, which is genuine invocation context beyond the annotation set.

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 sentences, front-loaded with the action and scope, then the return shape, then the minimal-call note. Nothing is repeated from the title and no sentence is filler.

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-value burden and does so well, enumerating links and the report subfields. Minor gaps remain: the possible status values and whether finished results expire are not stated.

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 explains kind, task_id, and job_id. The description still adds a decision rule the schema only hints at: one job_id replaces the task_id + kind pair, so an agent knows the minimal two calling paths rather than assuming all fields are needed.

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?

States a specific verb and resource ('check an async doseedo job once') and immediately scopes it to the two job types it covers, naming doseedo_convert_project and doseedo_bounce_session as their producers. An agent can distinguish it from wait/list/cancel siblings without opening the schema.

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?

The word 'once' implies poll-again semantics and the description limits it to conversion and bounce jobs, which is real scoping. It does not say when to prefer doseedo_wait_task over repeated checks, nor what to do while the job is still running, leaving the main usage decision to inference.

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