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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds meaningful context beyond them: the email goes to the client on file, it requires the Pro plan, it needs a Cotlet API key with app access, and it reaches other people. This is solid behavioral disclosure for a send action.

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 purpose is front-loaded, but the first two sentences are redundant ('Email an estimate to the client' / 'Emails one estimate to the client on file'), and the 'Service Autopilot:' prefix repeats the title. The remaining sentences (plan, confirmation, API key) are distinct and useful.

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 single-parameter send tool with no output schema, the description covers the key call-relevant facts: what gets sent, to whom, the plan gate, the confirmation requirement, and the credential needed. Only the exact outcome/side effects of the send are unspecified, which is minor.

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 100% and the schema already documents estimate_id ('Estimate ID from list_estimates or create_estimate'), so the baseline is 3. The description adds nothing about the parameter beyond what the schema provides.

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 ('Email an estimate to the client') and narrows the scope ('one estimate to the client on file'), which cleanly distinguishes it from create_estimate and list_estimates siblings. An agent can tell what it does 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?

It gives actionable confirmation guidance ('confirm with the user before each call', and that confirmation can be switched off for this tool), which is genuine usage context. However, it never says when to choose this over alternatives like create_estimate or list_estimates, nor any prerequisites for the estimate being ready to send.

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