save_draft

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

With no annotations provided, the description takes on the burden of behavioral disclosure. It passes the most critical behavior: the tool does not send the email, only saves it as a note, and the user must send via the UI. This goes beyond the basic verb and adds meaningful workflow context. It could mention side effects (e.g., whether the note is visible on the prospect record) but the key non-sending behavior is well covered.

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 two sentences long and front-loads the core action in the first sentence. The second sentence adds essential clarification ('Does NOT send') without redundancy. Every sentence earns its place, making it highly efficient and easy to scan.

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 save-draft tool with no output schema and no annotations, the description provides the essential context: purpose, non-sending behavior, and the follow-up workflow (review and send from the UI). It could be richer by explaining what a 'note' means on the prospect record, but the core usage context is adequately covered.

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?

The input schema has 0% description coverage for parameters, and the tool description adds no semantic information about the parameters. While parameter names like prospect_id, subject, and body_html are somewhat self-explanatory from the context, the description does not explain relationships such as body_text vs body_html or whether body_text is required. With zero coverage, the description needed to compensate but fell short.

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 clearly states the action: 'Save a drafted email as a note on a prospect.' It uses a specific verb ('save') and resource ('note on a prospect'). It also distinguishes itself from a sending tool with the explicit 'Does NOT send' and points to the linklight UI for the actual send, preventing confusion with sibling tools like draft_email.

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 provides clear context for when to use the tool: to save a drafted email without sending it. The explicit 'Does NOT send — user must review and send from the linklight UI' serves as a when-not-to-use directive, implying the tool is for drafting/note-saving rather than sending. However, it does not explicitly name alternative tools or exclusions, so it stops 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.