Send estimate

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

Annotations already indicate readOnlyHint=false and openWorldHint=true, so the action is known to be mutating and have external effects. The description adds value by explicitly stating 'this emails/texts the customer,' which reveals the specific external communication side-effect beyond the annotation hints. It does not detail potential consequences like duplicate sends or costs, but with annotations covering the overall openness, this is sufficient.

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 sentences with zero filler. The primary purpose is front-loaded, and the outward-facing note adds critical context in a compact second sentence. Every word earns its place; this is an exemplar of concise description.

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 send action with five params (one required) and no output schema, the description covers the essential purpose and the external impact. It does not mention the ability to test-send via liveMode or the need for a valid contact channel, but those are conveyed in the parameter descriptions. It is complete enough for an agent to invoke correctly, with minor gaps around prerequisites and post-send 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?

The schema covers 80% of parameters with descriptions (action, userId, liveMode, locationId), leaving only estimateId undocumented. The description does not add parameter-specific insights, but the schema already provides adequate semantics. Since coverage is high, the baseline of 3 is appropriate; the description would need to compensate for gaps but does not.

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 ('Send an estimate to the contact') and specifies the outward-facing nature (emails/texts the customer). This distinguishes it from other send tools like ghl_send_invoice or ghl_send_message, which target different resources. The verb and resource are precise and unambiguous.

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 gives context (send to contact, outward-facing) but does not explicitly state when to use this tool versus alternatives such as ghl_send_invoice or ghl_send_message. It lacks explicit 'when to use' or 'when not to use' guidance, though the tool name and summary imply the use case. The context is clear enough for basic selection, but exclusions are not articulated.

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