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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) by disclosing the 25MB attachment limit, the failure mode when no email exists and none is passed, the side effect of marking the invoice 'Emailed' in history, the default per-call confirmation, and the API-key access requirement.

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?

Purpose and destination are front-loaded, and each sentence carries distinct operational information (limits, failure mode, side effect, confirmation, auth). It is on the longer side at eight sentences, but little of it is filler.

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 operation with no output schema, it covers everything an agent needs: recipient resolution, attachment limits, failure behavior, resulting invoice state, confirmation requirement, and credential scope.

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 the schema already documents all six parameters including the 'to' default and cc/subject/message. The description reinforces the 'to' default but adds no syntax or format detail beyond the structured fields, making the 3 baseline appropriate.

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 (email/send) and resource (invoice) plus the mechanism (PDF attached, from the Share > Email invoice menu). An agent can distinguish this from sibling myob_create_invoice, myob_get_invoice, and myob_send_customer_statement 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 clear triggering context: it sends to the customer-card address unless 'to' is passed, and requires user confirmation because it reaches other people. It does not name alternatives (e.g., send_customer_statement) or explicitly exclude cases beyond the missing-email failure, so it falls short of a full 5.

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