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

Annotations already declare non-readOnly, destructive, and open-world, yet the description adds genuinely new behavioral context: creates trigger outreach gates and notifications, each create emits a separate message even for repeated text, updates are limited to your own message, and edits/deletes cannot recall already-delivered email. That last point is exactly the kind of irreversibility detail an agent needs before calling a destructive tool.

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?

Front-loaded with purpose and then layered by increasing specificity, with no filler sentences. It loses a point only because the parameter-requirement sentence duplicates what the schema and its required[] array already state.

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 four-parameter mutation tool with no output schema but with annotations covering the safety profile, the description supplies everything needed to call it correctly: ownership limits, notification side effects, non-recall of delivered mail, and routing for out-of-scope content. Nothing material is missing.

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 already 75% and the schema documents all four parameters, including the action-conditional requirements. The description largely restates those same facts (deal_id required everywhere, message_id for update/delete, message max 65535 chars) without adding format or validation detail beyond the schema, so the 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?

The first sentence gives a specific verb set (create/update/delete) and a specific resource (client-facing messages on a deal), which cleanly separates it from the read sibling deal-message-read. It further disambiguates from deal-activity-write by explicitly stating that internal notes belong there.

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?

It states when to use it (client-facing messages, with create/update/delete variants), when not to use it (internal notes -> deal-activity-write; staff-only messages are rejected outright), and the per-action parameter preconditions. The routing rule to the alternative sibling is explicit rather than inferred.

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