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

Annotations already declare non-read-only, non-destructive, non-idempotent behavior. The description adds important beyond-annotation context: the tool returns text only, nothing is sent, it consumes 1 AI credit, and merge fields can keep output reusable. These are non-obvious behavioral and cost traits.

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 compact paragraphs: the first front-loads purpose and the critical 'nothing is sent' constraint, while the second covers cost and merge-field reuse. No sentence feels redundant.

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 four-parameter generation tool with no output schema, the description covers output nature (text only), send behavior (nothing sent), cost (1 AI credit), personalization, and merge-field reuse. It does not explicitly state whether the draft is persisted, but that is a minor gap given the annotations and schema.

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?

With 100% schema coverage, the baseline is 3. The description adds meaning beyond the schema by explaining that owner_id/property_id personalize with real owner and property data, and by documenting merge-field syntax with examples and a related resource.

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 verb and resource: drafting email, SMS, or direct-mail messages with Spur's AI. It distinguishes itself from sending siblings by saying 'nothing is sent,' but does not explicitly differentiate from close siblings like spur_preview_message_draft or template-creation tools.

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?

The description implies usage when AI-generated draft text is needed and nothing should be sent, but it gives no explicit when-to-use/when-not guidance and does not name alternatives such as previewing a draft or creating a reusable template.

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