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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior: the result can legitimately be empty because clips may not yet be transcribed, and it names the remediation tools.

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, front-loaded with the primary purpose and return shape, then the fallback behavior. No filler and nothing repeated from the schema or annotations.

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 no output schema, the description does the work of describing the return: spoken words with start/end in seconds. It omits how the transcript is structured (per-clip grouping, ordering, field names), which is a minor gap for a read tool.

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?

Only one parameter (project) and schema description coverage is 100%, with the schema pointing to list_projects/create_project for the id. The description adds no further meaning about the parameter, so this sits at the baseline for fully documented schemas.

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 resource ('the spoken words of the project's clips placed on the timeline') with scope detail (start/end in seconds) and conditions ('when the clips have been transcribed'). It explicitly contrasts with the sibling get_media_transcript, so an agent can distinguish the two without opening either schema.

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?

Clearly signals the alternative path when the result is empty: use get_media_transcript (which also handles files not on the timeline) or run the addCaptions op. It doesn't state a general when-to-prefer rule up front, but the empty-result routing is concrete and actionable.

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