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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered without the description. The description does add two genuinely extra facts: the page size ceiling and that 'take is null for audio without a retained narration take', which clarifies a return-state edge case. With an output schema present, that return-value note is the main additional value, so a middling score is warranted.

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, front-loaded with the returned data, then pagination, then the edge case. No filler. Minor deduction for jargon ('take', 'retained voice inputs') used without definition.

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-value detail is not required, and annotations cover the safety profile. What is missing is the meaning of the required assetId and the optional workspaceId scoping (does omitting workspaceId change results?), which matters for a tool that reads per-asset narration state. Adequate but incomplete for a 4-parameter read tool.

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 50%: assetId and workspaceId are documented only as 'UUID string.', while limit/offset carry no schema description at all. The description partially compensates by explaining limit (default 200, max 500) and offset (selects the next page), though the default/maximum values merely restate schema constraints. It adds nothing about assetId or workspaceId scoping, so the baseline 3 holds.

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 ('Read') and resource (retained narration data: voice inputs, duration, audio SHA-256, word timing). An agent knows exactly what payload it gets. However, it never distinguishes itself from adjacent siblings like media_transcript_get or media_assets_get, which could also surface audio/timing data, 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?

There is no when-to-use guidance, no prerequisites, and no named alternative. The pagination sentence ('Defaults to 200 words, maximum 500; offset selects the next page') is invocation mechanics, not selection guidance. The agent must infer this is the narration-timing reader purely from the name.

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