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

The readOnly/idempotent/non-destructive annotations already cover the safety profile, and the description adds genuine operational context by framing this as a polling endpoint that should be called with a delay. It does not disclose what progress states or completion signals come back, which is the behavior an agent polling a job most needs to reason about.

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 tight sentences, no padding, with the usage instruction front-loaded before the recovery warning. Slight vagueness in 'check' costs it the top mark, but nothing is wasted.

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?

A simple one-parameter, read-only, idempotent tool with an output schema, so return values need not be described. Still, the definition leaves the projectId precondition underspecified and gives no signal for choosing between this and the other project-read siblings, which is the main gap.

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 projectId, and the description does not compensate: it never explains that projectId is the identifier of an already-created project or what form it takes. The phrase 'a project already started' hints at the precondition but adds no real meaning beyond the schema.

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?

"Check a project already started" names a resource and a loose verb, but 'check' does not distinguish this poll-for-status tool from siblings like dub_get_project or dub_get_project_result. The agent must infer from the title ('Check translation progress') that this returns progress rather than project metadata or final output.

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?

Explicitly says to poll with a delay and warns against creating a new project to recover progress, which is a concrete anti-pattern worth stating. It stops short of naming when to switch to dub_get_project_result or dub_get_project, so routing among the read siblings remains implicit.

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