Download a call recording

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

Goes beyond the annotations by disclosing the required permission scope (recordings:read), the fact that a file is written to disk, and that the local path is returned. It does not cover overwrite behavior when the target file already exists or any size/rate constraints, which keeps it from 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?

Two dense sentences with zero filler; the endpoint and permission are front-loaded, followed by the behavioral outcome and input provenance. Every clause carries information an agent needs.

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 two-parameter download tool with no output schema, the description covers permission, side effect, return value, and input sourcing. The only gap is failure modes (missing recording, unwritable path), which are not addressed anywhere.

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 coverage is 100%, so the baseline is 3, but the description adds genuine provenance for `file` (the `filename` field from list_recordings or a call.ended webhook) that the schema's format example does not convey. `outputPath` is left entirely to the schema, which documents its default well.

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 ('Saves the audio file to disk and returns its local path') plus the underlying endpoint, so the agent knows exactly what happens. It also implicitly distinguishes itself from the sibling list_recordings by naming that tool as the source of the input.

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 the required input: '`file` is the `filename` field from list_recordings (or from a call.ended webhook)', which routes the agent to the right upstream call. It stops short of stating when not to use this tool or what happens if the recording is already local.

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