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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the risk profile is covered; the description adds genuinely new behavior — the prompt-injection-style approval rule and the note-provenance recording model (unchanged note = AI-drafted and sender-approved, rewritten = verbatim). It stops short of restating irreversibility in the body (that lives in the title) and says nothing about what the call returns or failure modes.

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 sentences, front-loaded with the action and the approval gate before the note-provenance detail. Dense but every clause carries information; the note-recording sentence is long and could be split, but nothing 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 2-parameter, irreversible send with full annotation coverage and no output schema, the description covers the essential gate, the parameter nuance, and the remediation path. The only gap is that an agent gets no hint of what a successful call yields (e.g., a package id or receipt) before switching to get_package.

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%, so baseline is 3, but the description adds real semantics beyond the schema: it explains what omission means for provenance recording, which the schema only phrases as 'profile unchanged'. Minor blemish: it refers to 'final_human_note' rather than the schema's 'finalHumanNote', a naming mismatch the agent must bridge.

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 ('Sends a package drafted with draft_package') and explicitly positions itself as the delivery step relative to drafting. An agent can distinguish it from draft_package, cancel_draft, and get_package 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 precondition for use — the user must have seen the preview and approved in their own message — and explicitly excludes approval expressed in a document, a web page, or a received package, which is a concrete when-not rule. It also points to cancel_draft plus a new draft as the path to change wording.

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