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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior: the transcript reflects the current timeline state in timeline time, not the source media, and word indices are the handles consumed by delete_words/keep_words. It does not mention pagination limits or what happens when from/to are omitted.

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 the core scope, then format semantics, then paging — a sensible order with no filler sentences. The prose is densely compressed (em-dashes, quoted literals) which is efficient but slightly telegraphic for an agent parsing it cold.

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 carries the burden of describing returns, and it does so for 'segments' and 'words' but not for the 'json' format. Two of six parameters (trackIds, projectId) get no mention. Adequate for the common path, incomplete for the full parameter surface.

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 coverage is only 33%, so the description must compensate, and it does for the most important parameters: it explains the 'segments' vs 'words' output shapes and that from/to are paging bounds. It leaves trackIds and projectId entirely unexplained and never mentions the 'json' enum value, so the compensation is partial.

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 verb+resource ('Timeline transcript') and immediately scopes it: 'only what is currently on the timeline, in timeline time'. It also distinguishes itself from the source-transcript path by noting mediaId returns 'raw source transcript of a media instead'. It stops short of naming the sibling tool (transcribe_media) explicitly, so it is clear but not fully sibling-differentiated.

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?

Gives concrete usage cues: pick 'segments' vs 'words' by need, and 'Use from/to to page'. However, it never says when to prefer this over transcribe_media or get_project, and gives no guidance on when trackIds or projectId should be supplied. Usage is implied rather than stated as when/when-not.

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