media.director.review

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

With no annotations, the description carries the full behavioral burden, but it only says the QA is 'deterministic.' It does not disclose whether the operation is read-only, whether it creates background jobs, mutates project state, or requires prior generation. This is a significant gap for a review action.

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?

The description is a single focused sentence with no filler. 'Deterministic' adds meaningful nuance, and the core action is front-loaded. It could be slightly more informative, but as conciseness goes, it is well structured.

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?

There is no output schema and no annotations, so the description must explain what happens when the tool is called. It does not clarify whether results are returned directly, whether a job is spawned, what project state is required, or what side effects occur. An agent can guess the intent but not the operational behavior.

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?

The schema lists required projectId but defines no properties, and context reports 100% schema coverage, so the baseline is 3. The description adds no parameter-level meaning beyond implying the project to review, which is fairly self-evident from the parameter name.

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 uses a specific verb ('Run') and resource ('deterministic continuity/shot QA'), making the tool's purpose clear and distinct from generation, status, or flow tools. It does not explicitly contrast with a sibling, but the operation is well identified.

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?

There is no guidance on when to use this tool versus alternatives like media.video.generate, media.job.status, or media.flow.handoff. The phrase implies a post-production QA step, but prerequisites and when-not-to-use conditions are absent.

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