draft_enquiry

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

Annotations declare non-destructive, non-open-world, additive behavior; the description adds meaningful context beyond that: the draft is editable, it 'does not send or log a contact' (distinguishing it from log_contact), and it pulls local sender/insurance preferences. Strong value-add, though it doesn't cover rate limits or what the draft object contains.

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?

Four sentences, each earning its place, with the core purpose front-loaded. Slightly more could be trimmed, but every sentence conveys actionable constraint information.

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?

An output schema exists, so return values are documented elsewhere, and preconditions plus the no-send/no-log guarantee are captured. The one gap is parameter-level documentation for a 5-param tool, which is only partially compensated.

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 0% across 5 parameters, so the description must carry the load. It implicitly maps several ('saved therapist' for profile_id, 'follow-up drafts' for kind, 'health details' for additional_context, verified 'recipient'), but never explicitly explains kind/language enums or additional_context limits, leaving gaps it should have closed.

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+resource ('Create an editable email draft for a saved therapist') and clearly distinguishes itself from siblings like get_email_draft, update_email_draft, and export_email_draft via the creation verb and 'editable' qualifier. An agent can identify the operation 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?

Provides real preconditions: follow-up drafts require a recorded earlier enquiry, and a missing email requires a verified recipient. It also constrains input ('only include health details explicitly supplied'). It stops short of naming alternative siblings to route to, keeping it at a strong 4 rather than a 5.

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