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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly covered. The description adds valuable behavioral context: it returns text and sends nothing, and it consumes the workspace's AI budget, which is a non-obvious side effect. It does not describe rate limits or error 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?

The description is a single, front-loaded sentence that packs many actions but wastes no words. The list of rework actions is dense but necessary for understanding the full scope; structure could be improved with bullets but is acceptable.

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?

Given five parameters, an enum, no output schema, and annotations covering safety, the description is nearly complete. It explains the tool's output ('returns text'), its non-sending nature, and the AI budget cost, but could clarify that the returned text is a draft to be sent by another tool.

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 schema documents all five parameters. The description adds semantic meaning to the action enum by explaining each mode (e.g., 'answer only from the help articles', 'rework a text (shorter, friendlier, formal, fix spelling, translate)'), which goes beyond the bare enum values.

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 states a specific verb and resource: use the workspace's AI model to draft, answer, summarise, or rework. It distinguishes itself from sending tools by stating 'sends nothing', so an agent can tell it apart from reply_to_conversation without opening the schema.

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 provides clear context for when to use it (to generate AI text without sending) and notes the AI budget cost, but does not explicitly name alternatives like reply_to_conversation or save_reply_draft or state when not to use it. The implied usage is clear but lacks explicit routing.

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