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

Annotations already establish that this is not read-only, not destructive, and not idempotent. The description adds important context beyond that: the tool does not persist anything and returns only the generated text, so the caller must save it separately with create_ or update_proactive_message.

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 tightly written sentences: the first states the action, the second states the critical non-persistence behavior and next step. There is no filler, and the important save requirement is front-loaded after the purpose.

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 correctly states that only text is returned and tells the agent how to persist it. It is nearly complete for a generation tool, though it does not mention prerequisites such as AI settings being enabled or any failure behavior.

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 description coverage is 80%, so the schema already carries most parameter meaning. The description does not add detail about productId or instruction and only loosely maps 'text' to the text parameter, so it remains at the baseline for a well-covered schema.

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: using the workspace AI to draft or rework text for a chat message, pop-up slide, or banner. It also distinguishes itself from the sibling save tools by saying it only returns text and must be followed by create_ or update_proactive_message.

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 clear post-use routing by naming create_proactive_message and update_proactive_message as the save step, which is exactly what an agent needs after drafting. It does not explicitly contrast with other AI-generation siblings such as draft_reply_with_ai, so it falls short of full alternative coverage.

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