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

Annotations declare the write profile (readOnlyHint=false, openWorldHint=true, non-idempotent), and the description adds non-obvious behavior on top: fake/placeholder payloads under 1 KiB or bare headers are refused without transcription. It also discloses the return shape (transcript + capture id), which the annotations do not cover.

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 core action, then limits, then validation, then the fallback. Efficient overall, though the final sentence about the Captures page is somewhat long and could be tighter.

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?

Covers input constraints, validation failure modes, and the fallback path, and an output schema exists so return values need not be spelled out. Nothing essential for correct invocation is missing.

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 mutual-exclusivity rule, format list, and size limits are already documented in the schema. The description restates these (10 MiB, format list, 'real bytes') but adds little parameter-level meaning beyond the schema baseline.

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?

Opens with a specific verb+resource ('Transcribe an audio file to text') and names the engine (VoiceLabs' Whisper), which cleanly distinguishes it from siblings like speak and list_captures. An agent can identify the operation without opening the schema.

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 states the exactly-one-input rule (audioUrl or audioBase64) and provides a concrete fallback workflow when the agent cannot read the bytes: ask for a public link or direct the user to the Captures page. Conditions for each path are stated rather than implied.

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