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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false, but the description adds real operational context they don't carry: irreversibility ('once sent it cannot be recalled'), the aggregate recipient cap (10 across to+cc), one-message-per-call semantics, and that the plain-text body is rendered as HTML. This is exactly the value-add expected when annotations exist.

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?

Dense but front-loaded: the write/irreversible warning comes first, then constraints, then the new-vs-reply distinction, then the endpoint. Every sentence carries a distinct constraint; nothing is redundant padding.

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 high-risk mutation with no output schema, the description covers irreversibility, recipient limits, and message semantics thoroughly. It stops short of stating what the call returns or any permission/scope requirement on the inbox, but the critical call-correctness information is present.

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 baseline is 3. The description goes beyond it by stating the combined cap of 10 recipients across to+cc — a cross-parameter constraint the JSON schema cannot express (maxItems would allow up to 19) — and by explaining the body's plain-text-to-HTML conversion. It adds genuine meaning without restating individual field descriptions.

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 — sending a real email from a named Helpwise inbox to given recipients — and explicitly distinguishes itself from the closest sibling behavior by noting it starts a new message rather than replying on a conversation (contrast with helpwise_add_note). An agent can route correctly without opening the 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 explicit exclusions and conditions: 'never use it for lists or campaigns', 'one message per call', 'this starts a new message (it is not a reply on an existing conversation)'. That is when-not-to-use guidance tied to named alternatives, not vague implication.

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