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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true; the description adds real value on top — it flags irreversibility ('this is a real outbound email'), the do-not-contact safety branch, and the timeline logging side effect. It does not mention rate limits, attachments, or queuing behavior.

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 short sentences, front-loaded with what it does, then safety behavior, then the confirmation caution. No 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?

With an output schema present and rich annotations, the description covers the essentials an agent needs: identity, side effects, safety failure mode, and the confirmation requirement. Minor gaps (attachments, delivery timing) are not blocking.

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% and every parameter (contact_id, subject, body, cc, bcc) is documented in the schema, so the description adds no parameter-level detail beyond it. Baseline 3 applies.

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?

Specific verb+resource ('Send an email to a contact') plus the sender identity and the side effect of logging on the contact timeline. This distinguishes it from timeline-only siblings like add_note and makes clear it is a real outbound send.

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?

States a hard precondition ('Fails safely if the contact is marked do-not-contact') and a required pre-send step ('Confirm the subject/body with the member'). Clear context for when to use it, though no explicit alternatives are named.

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