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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds genuinely new traits: zero cost and the downstream billing effect on burn_captions. It also clarifies that edits are a full replacement of cues rather than a merge. Missing: what happens to the previous cues or the returned job state.

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 short, front-loaded sentences with no padding; the primary action and the cost caveat come first. The telegraphic fragments ('Cost is zero.') are efficient rather than noisy, though they read slightly clipped.

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-parameter mutation tool with no output schema, the description covers the cost model and input formats but omits return behavior, whether the job must already be complete, and cue timing units. An agent could invoke it but might guess wrong on payload format or state assumptions.

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?

With 0% schema description coverage the description has to compensate, and it partially does by naming the two optional inputs and the accepted subtitle formats (SRT, VTT, JSON). However, it never explains jobId, whether cues and subtitles are mutually exclusive or which wins, or the units for start/end (seconds vs. milliseconds) — a significant gap for a timing-critical payload.

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: 'Replace the cues on a finished transcription.' The phrase 'without running Whisper again' implicitly contrasts it with transcribe, so an agent can distinguish the edit path from the re-transcription path. It stops short of naming a sibling tool explicitly, which keeps it from 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 clear context for use: after transcription is finished, before caption burning, and explains the cost relationship with burn_captions (passing this transcriptionJobId charges only the burn price). No explicit exclusions or preconditions (e.g., job must be in a completed state) are stated, so it falls short of a 5.

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