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

Goes well beyond the readOnly/idempotent annotations: states it costs no minutes or credits, that repeating a voice+text pair is free and unlimited while new previews are capped at 10/hour and 30/day per workspace, that it mutates nothing, and that some voices fail with a suggested workaround. This is the kind of operational detail annotations cannot express.

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?

Five tight sentences, front-loaded with what it does and the MP3 return, then the approval workflow, then cost, then rate limits, then the failure mode. No sentence restates the name or the annotations and each adds distinct 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 (MP3 link the owner can open and play) and also covers cost, throttling with a dedup exemption, and the unsupported-voice failure path. An agent has everything needed to call it and to interpret success or failure.

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 meaning: text is a draft versus the saved greeting, and the preview is spoken in the receptionist's own voice. The enum values for greeting are documented in the schema rather than the description, so this stops short of a 5.

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 concrete verb and resource ('Speak a receptionist's greeting') plus the concrete artifact returned ('a link to an MP3'). It also draws the line against the sibling it is most likely to be confused with by positioning itself as a pre-check before updateAgent saves.

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?

Usage is clearly contextualized: it is the approval step for wording before updateAgent persists changes, which tells the agent exactly when to reach for it instead of the update tool. It also names a fallback path ('suggests a test call') when a voice cannot be previewed, though it does not name the sibling tool that performs that call.

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