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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real value beyond them: availability limits (older exports, unverified speech) and an explicit non-fabrication contract against titles and edited timelines.

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 that are front-loaded with the core action and then the failure semantics. Dense but each clause carries information; the second sentence is slightly overloaded but earns its place.

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?

An output schema exists, so return values need not be explained, and the description covers the key behavioral edges for a read-only two-parameter tool. The only real gap is parameter meaning, which is minor against the otherwise complete behavioral picture.

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 only 50%: exportId carries a bare 'UUID string.' and workspaceId has no description at all. The description adds nothing about what either parameter means or how workspace scoping interacts with the export, so it fails to compensate for the coverage gap.

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 (Read) plus a precisely scoped resource: a WebVTT caption track from the completed export's immutable canonical speech snapshot. It distinguishes itself from transcript and caption siblings by anchoring to the export snapshot preserving actual trims, so an agent can tell it apart without opening a 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 states the when-not conditions: 'Returns unavailable for older exports or unverified speech' and refuses to work from titles or current edited timelines. It does not name a sibling alternative (e.g. media_transcript_get) for the unsupported cases, so it stops short of full routing guidance.

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