transcribe_voice_note

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

Annotations declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely new behavioral context: the default provider is groq and using 'local' prevents the audio from leaving the machine, which tells the agent about data egress. It still omits rate limits, size limits, and failure behavior.

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?

Two tightly written sentences; the core action and both input modes are front-loaded with no filler.

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 should say what the transcription returns (text inline? stored on the message?) and how multiple attachments are handled when rowid is given. Those are real gaps for a tool whose result shape is otherwise unexplained.

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 all three parameters are already documented. The description restates the path/rowid duality and the provider default but adds no format or constraint detail beyond the schema, 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?

States a specific verb and resource ('Transcribe an audio attachment to text') and immediately clarifies the two ways to identify the audio. It is clearly distinguishable from siblings like speak, send_file, or search_messages.

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?

Explains the two input modes (message rowid vs. absolute path) and notes the default provider, plus the tradeoff that 'local' keeps audio on this machine. It stops short of explicitly stating when to prefer one mode over the other or naming an alternative tool.

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