List transcript fixes

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

With readOnlyHint already declaring the safety profile, the description adds real value: it discloses the return shape, the meaning of the flags' content ('misheard names, fillers and repetitions to cut, and your own cuts and corrections'), and the status semantics that drive the next action. It stops short of describing ordering, pagination/truncation behavior at the limit, or what an empty result looks like.

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?

Front-loaded with the resource and its contents, then the return shape, then the actionable next step — no filler sentences. The inline brace-notation return schema is dense but earns its place since no output schema exists.

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, three-parameter listing tool with no output schema, the description supplies the return structure, the flag taxonomy, and the workflow link to review_transcript_flags — enough to call it correctly. Remaining gaps (result ordering, behavior when limit truncates) are minor for a listing operation.

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 enum descriptions already define pending and auto ('waiting for review', 'applied automatically'), so the description's 'status pending waits for your decision' largely restates structured data. The description adds indirect context about what the ids are for, but no new constraint or format details beyond the schema, so baseline 3 is warranted.

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 ('the fixes Reelsaw made or suggests in a project's transcript') and enumerates the categories of flags returned, which distinguishes it from get_transcript and from the mutating sibling review_transcript_flags. An agent can tell at a glance that this is a read-only enumeration of reviewable corrections.

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 routes the agent forward: 'Use the ids with review_transcript_flags', and explains that 'status pending waits for your decision', which frames the review workflow. It does not state when to prefer get_transcript or add_transcript_cut/add_transcript_correction instead, so the exclusion side is implied rather than spelled out.

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