Check project / wait for a job

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

Annotations declare readOnlyHint=true, consistent with reporting status. Description adds behavioral detail: polling semantics (wait up to ~50s), returned data (duration, audio presence, 4 QA frames), and post-use actions (adjust focalX/focalY). No contradiction.

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 primary purpose, then conditional details. Every sentence provides value without redundancy. Length is appropriate for the information conveyed.

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?

Covers return values, timeout, and actionable QA instructions. Lacks details for error handling (invalid slug) and the 'build' option. Overall sufficient for the tool's complexity.

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%, so description must compensate. It explains two of four enum values for wait_for (voiceover, render) and their behavior, but does not clarify 'build' or 'none' (default). Slug parameter is obvious. Partial compensation.

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 clearly states the tool reports voiceover and render progress for a project, with specific wait behaviors. It distinguishes from siblings like render_video and generate_voiceover by focusing on status checking rather than initiation.

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?

Provides clear usage context: when to call (after initiating processes), how to interpret output (inspect QA frames, adjust parameters), and retry advice ('If a job is still running... call again'). Does not explicitly contrast with alternatives but implies its role.

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