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

Annotations already establish the safe-read profile (readOnlyHint, destructiveHint=false, openWorldHint). The description adds genuinely non-obvious behavior: character-based paging driven by next_offset, and the speaker_channel requirement for multichannel jobs. It does not cover rate limits or exactly what the payload contains, keeping it short of 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, front-loaded with what the tool returns, followed by the paging rule and the multichannel rule, closing with the endpoint. No filler and every clause carries actionable information.

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 carries the return-value burden and does so adequately by stating the payload is SRT or WebVTT and is paged via next_offset. Missing only minor detail such as the response shape of next_offset alongside the caption text.

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%, so the parameters, their bounds, and defaults are already fully documented in the schema. The description echoes the format default and the offset/speaker_channel semantics without adding syntax or constraints beyond what the schema states, matching the baseline 3.

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+resource ('Captions for a transcribed job') plus the two output formats and the underlying endpoint GET /jobs/{id}/captions. The resource is inherently distinct from siblings like revai_get_transcript and revai_get_summary, though the description never explicitly names those alternatives to sharpen the contrast.

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 concrete operational guidance: repeat the call with next_offset until it is null for long files, and pass speaker_channel for multichannel jobs. It does not however tell the agent when to prefer captions over the sibling revai_get_transcript, so there are no stated exclusions.

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