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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful return-shape context (program timestamps, source spans, repeated-phrase detection) that annotations cannot convey. It stops short of saying whether the result reflects the current edit state live or a snapshot, and the idempotentHint=false on a pure read is left unexplained.

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?

One dense sentence with the payload characteristics enumerated in a natural order and no filler. It is front-loaded on the outcome and could only be improved by adding a routing clause rather than trimming anything.

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 does the right thing by naming the returned fields, and the single required parameter is fully documented in the schema. What is missing for a tool of this type is the relationship to the underlying edit lifecycle (does it require a prior keep_segments or an open project?) and any sense of result size or pagination.

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 the single project_id property already documents that the navigation pointer does not select the target. The description adds nothing about the parameter, 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?

The description gives a specific verb ('Returns') and a clearly scoped resource: the transcript retained by the current edit, as opposed to the full transcript. That distinguishes it in spirit from siblings like get_transcript, get_words and search_transcript, but the key concept ('kept' = post-cut retention) is never spelled out, so an agent must infer it from the name.

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 explicit when-to-use guidance and no named alternative. With get_transcript, get_words, get_syllables and search_transcript all in the sibling list, the description never says 'use this after keep_segments' or 'use get_transcript for the untrimmed version', leaving the routing decision to inference.

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