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

Annotations already declare destructiveHint=true and openWorldHint=true, so the external, irreversible nature is partly known; "Can't be undone" restates that rather than extending it. The genuinely additive content is the human-confirmation protocol and the fact that the customer receives a signable review link, which no annotation conveys. It stops short of saying what the call returns or what happens on an invalid/already-sent estimate.

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?

Three short sentences, front-loaded with the effect, then the confirmation gate, then the irreversibility warning. No filler and nothing buried.

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?

The safety and workflow picture is solid for a destructive outbound action, and there is no output schema to explain. However, with 0% schema description coverage the description leaves both parameters undocumented, including the optional note, which is the only field an agent could get wrong beyond the ID. Adequate for the side effect, incomplete for the inputs.

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 description coverage is 0%, so the description must carry parameter meaning and it does not: neither estimate_id nor the optional note (max 500 chars) is mentioned. "Title, total and the email it goes to" are estimate attributes the agent should read aloud, not input parameters, so they don't compensate. An agent would not know from this text what note does or that it exists.

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 or proposal to its customer") and anchors it to a known UI action ("the same email as the Estimates page Send button"), plus the payload ("a link to review and sign"). The resource noun alone separates it from send_invoice, send_text and send_pay_link without opening any 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?

Gives an explicit gating condition: "First tell the owner the title, total and the email it goes to. Only call after the owner says send." That is a concrete when-to-use / when-not-to-use rule an agent can execute, rather than an implied one.

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