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

Goes well beyond the annotations by disclosing that only the inbox's own person can read/send, that the same mailbox works via Corply and IMAP/SMTP, that replies must carry messageId/references, and that message contents must be treated as untrusted data. The trailing generic boilerplate about 'canonicality', 'idempotency' and a 'confirmation boundary' that says no confirmation is needed for 'this read' is confusing for a send tool and dilutes the otherwise strong disclosure, so it falls short of a 5.

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 front half is well front-loaded and earns its place, but the final three sentences (canonicality, idempotency, confirmation boundary) are boilerplate that reads as copy-pasted policy text and contradicts the tool's own confirmation requirement.

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?

Covers the threading mechanics and confirmation/safety context well, but with 8 parameters including a nested context object, no output schema, and openWorldHint=true, the description never explains what the tool returns or how the receipt/id context is produced.

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% across 8 parameters, so the description carries the burden. It explains only inReplyTo and references; to, cc, subject, text, inboxId and the nested _corply_context object (with id/receipt dependentRequired) are left undocumented, leaving several parameters opaque.

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 ('Send an email') plus scope ('from the signed-in person's company address' / company inbox). An agent can distinguish it from siblings like send_invoice or list_inbox_messages without opening a 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 invocation context: it must be preceded by explicit confirmation of recipients/subject/text, and it explains the reply path via inReplyTo and references. It does not, however, name which sibling to use instead for adjacent tasks (e.g. read_inbox_message, send_invoice), so routing guidance is implied rather than explicit.

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