Tell the user out loud

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

No annotations are provided, so the description carries the burden and does well: it discloses the output modality (visual bubble plus spoken audio) and hard content constraints (one or two short sentences, plain text, no markdown). It does not cover failure behavior or whether the call blocks/interrupts ongoing speech, keeping it out of 5 territory.

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?

A single well-formed sentence with an embedded example and format constraints, front-loaded with the action. Every clause earns its place; nothing is padded.

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 one-parameter, side-effecting announcement tool with no output schema and no annotations, the description covers purpose, timing, and content format adequately. Minor gaps remain around error/failure behavior, but the tool is simple enough that this is nearly complete.

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 baseline is 3, but the description adds real meaning to the single 'text' parameter: it constrains length (one or two sentences), content type (plain text), and format (no markdown), which the schema's generic 'as it should be spoken' does not convey.

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 dual action: display a short update in VisionCLI's bubble AND speak it aloud. The medium and modality are unambiguous, and it is clearly distinct from voice/screenshot siblings like start_voice or device_screenshot.

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 a concrete when-to-use trigger ('when background work you promised to report on has finished') with an example. It offers clear context but names no exclusions or alternative tools (e.g., start_voice), so it falls short of a 5.

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