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

Annotations already declare readOnly/idempotent/non-destructive, so the description focuses on value-add: the NOT_FOUND behavior and the fact that absence of a transcript is expected rather than an error. It doesn't cover token expiry/session failure modes, but the failure-path disclosure is the most useful thing it could add here.

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?

Three tight sentences: what it returns, when it's unavailable, and how to use the result. Return shape is front-loaded and nothing is redundant.

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?

For a read-only, 3-param tool with full schema coverage and no output schema, the description supplies exactly what's missing: the return structure, the precondition, and the failure semantics. Nothing an agent needs in order to call it correctly is absent.

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 100%, with token, mediaRef, and projectId each documented in the schema including provenance (from connect/get_media/get_projects). The description adds no parameter-level detail beyond what the schema already provides, so the baseline 3 applies.

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 (Returns) and resource (word-level speech transcript of one media asset) and even sketches the return shape ({text, startSec, endSec}). This clearly distinguishes it from write-side siblings like start_transcription and generate_captions without the agent needing to open 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?

Explicitly states the precondition (only assets the user has transcribed have one), interprets the failure signal (NOT_FOUND means ask the user to run Transcribe on the clip in Frapea), and gives a downstream use case (use timestamps to align cuts). That covers when to use it and what to do when it isn't applicable.

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