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

Annotations only flag it as a non-idempotent, non-destructive write. The description adds material behavior beyond that: it consumes processing minutes proportional to processed duration and one magic credit when automatic mode is on. It still does not say whether the call blocks or runs asynchronously, nor what happens to credits on failure.

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, zero filler, and the precondition plus cost model are front-loaded rather than buried.

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 an output schema present, return values need no explanation, and the description covers precondition, cost, and the automatic-mode branch. It is nearly complete for a 3-parameter start action, missing only the async/blocking nature of the operation.

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 100%, so the schema already documents projectId, magic and startAtSec in detail; baseline is 3. The description only restates the magic/automatic-mode credit link, adding a little cost context but no syntax or format 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?

Specific verb plus resource: starts transcription and moment detection on a project, with the required AWAITING_CROP precondition named. An agent can distinguish it from delete_clip/update_clip/list_projects, though it does not explicitly differentiate from the nearby generate_clips sibling.

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 AWAITING_CROP precondition gives implied usage context, but there is no explicit guidance on when to choose this over generate_clips or retry_project, and no statement of what to do if the project is not in that status.

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