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

Beyond the annotations (destructive, open-world, non-idempotent), the description discloses the state transition ('A draft becomes issued'), resend behavior, and that a confirmation/owner-approval gate applies by default and can be disabled. That is substantive behavioral context the annotations alone do not convey.

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 first two sentences restate the same fact (emailing the invoice from Joist as its Send button does), which is redundant. The remaining content is front-loaded and useful, but the opening wastes a sentence.

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 write tool with no output schema, it covers recipient defaults, state changes on the document, resend semantics, and the approval/confirmation flow. The main omission is what the call returns on success or failure, though annotations and schema carry most of the burden.

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 100%, so all four parameters are already documented, including their defaults. The description restates the same defaults for 'to', 'subject', and 'message' rather than adding format, constraints, or edge-case meaning.

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 states a specific verb and resource ('Email the invoice to the client from Joist with its link and PDF') and clarifies the recipient's experience. It does not explicitly contrast with the sibling send_estimate, so it falls short of full sibling differentiation.

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 explains default behavior when 'to' is omitted and notes that drafts become issued and already-sent invoices can be resent, which implies when the tool is applicable. However, it never says when NOT to use it or names alternatives such as send_estimate, leaving routing guidance to inference.

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