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

Annotations already declare idempotent and non-destructive, but the description adds critical behavior: it waits up to ~15 s, returns rendering/done/failed, and with check:true fetches the MP4 into the workspace and runs vg deliver --check. This goes well beyond structured fields.

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-loads the core action and wait time, then covers returns, polling, and check behavior. It is dense but every clause earns its place; minor run-on quality keeps it from a 5.

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 polling tool with full schema coverage, an output schema, and annotations, the description covers wait time, return states, polling cadence, and the optional check side effect. Nothing an agent needs to call it correctly is missing.

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 documents all three parameters. The description restates the combined effect of check:true and projectId, but adds little semantic detail beyond what the parameter descriptions already say.

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 'Check' and resource 'an export started by video_project_export', immediately distinguishing it from the sibling that initiates exports. The return states are also named, so an agent knows exactly what this tool is for.

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 tells the agent when to use it: after starting an export with video_project_export, and to poll every 10-20 s. The guidance is actionable and leaves no ambiguity for this polling tool.

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