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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it clarifies that the tool only acts on the explicit project_id and never guesses the active project, and it distinguishes between source seconds and clip seconds. However, it does not disclose potential edge cases like missing transcripts or pagination, though these are minor given the read-only nature.

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 compact and front-loaded with the 'PROJECT-SCOPED' warning, then covers the core function, alternatives, and special case in a few sentences. Every sentence adds value, with no redundancy or filler. It is well-structured for quick parsing.

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?

Given the four parameters and no output schema, the description covers the essential aspects: what it returns, the time-range semantics, the alternative tools, and the asset_key option. It does not describe the exact return structure or error behavior, but for a read-only transcript fetcher, this is sufficient. The presence of sibling tools with clear distinctions further rounds out the context.

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?

With schema coverage at only 25% (only project_id has a schema description), the tool description must compensate. It does: it explains that project_id is required and immutable, start/end define a time range in source seconds, and asset_key switches to an uploaded clip's transcript. This adds meaning beyond the bare schema, though it could be more explicit about start/end format (e.g., inclusive boundaries).

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's function: retrieving sentence-level SOURCE transcript with timestamps for a time range in source seconds. It is specific about the resource (transcript), the granularity (sentence-level), and the scope (project-scoped with explicit project_id). It also explicitly differentiates from get_words and get_kept_transcript, making the purpose unmistakable.

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 description provides explicit usage guidance: it tells when to use get_words (word-exact timing) and get_kept_transcript (current EDIT), and explains when to pass asset_key (for uploaded clips/songs). It also emphasizes project-scoped behavior, implying the tool should only be used when project_id is available. This is excellent routing information.

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