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

Annotations mark this as a non-read-only, idempotent, non-destructive operation, and the description adds real value beyond them: the call is asynchronous and returns the project's analysis status rather than the transcript, with a named polling path. That async-workflow disclosure is exactly the kind of context annotations cannot convey; only the lack of any note on cost/duration or failure modes keeps it from a 5.

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: the action and its scope condition first, then the async return behavior and the exact follow-up tool chain. No filler, and the most decision-relevant fact is front-loaded.

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 3-param trigger tool with full schema coverage and annotations, the description covers what's missing from structured fields: that it forces transcription despite settings, and that the response is a status requiring polling rather than the transcript itself. Nothing critical is absent, though a note on how long transcription typically takes would complete it.

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 100% and all three parameters are documented in-schema (token, mediaRef from get_media, projectId from get_projects), so the baseline is 3. The description only hints that 'one asset' maps to mediaRef and adds no format or constraint detail beyond the schema.

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 and resource ('Transcribes one asset') plus the notable scope condition that it works even when automatic transcription is off. It does not distinguish itself from the sibling generate_captions, which an agent could reasonably confuse with this tool, so it falls short of a 5.

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 a clear trigger condition ('even if automatic transcription is switched off'; 'Speech transcripts otherwise appear on their own') and spells out the follow-up sequence: poll get_analysis_status, then read get_transcript. It lacks an explicit exclusion (e.g., when to prefer generate_captions instead), so 4 rather than 5.

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