Speak in the editor

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description adds real behavioral detail the annotations don't cover, notably that the ghost cursor moves to the anchored element and that mood tints the bubble. It also discloses a soft length guideline (~200 characters), though that is looser than the schema's maxLength of 1000, which could confuse an agent about the true limit.

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?

Three sentences, front-loaded with the core action, then usage examples, then parameter hints — no filler. The enumeration of all five mood values is slightly redundant with the schema enum and is the only padding.

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 simple three-parameter, no-output-schema UI tool, the description covers what the bubble is, where it anchors, when to use it, and how mood affects appearance. It omits what happens if the supplied element id doesn't exist and whether the bubble dismisses on its own, minor gaps for a tool of this complexity.

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?

At 67% schema description coverage, the baseline is around 3, and the description adds genuine meaning for two parameters: 'id' is explained as an anchor that also moves the ghost cursor, and 'mood' is explained as tinting the bubble, with its values spelled out. However, listing the enum values largely restates the schema enum, and the conflict between '~200 characters' and maxLength 1000 muddies the message-length semantics rather than clarifying them.

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?

The description opens with a concrete verb and resource: it shows a short speech bubble from the agent inside the user's editor, and it names the two anchoring modes (element id or top of canvas). This clearly separates it from the canvas-mutating siblings. It stops short of explicitly naming which sibling to use for adjacent needs (e.g. set_hud), so a 5 on sibling differentiation isn't earned.

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?

It gives three explicit when-to-use scenarios: explaining an upcoming change, pointing at lint findings, and asking the user something while they watch. There is no when-not-to-use guidance and no named alternative for overlapping tools like set_hud, which keeps it at 4 rather than 5.

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