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

Annotations only flag non-read-only, non-idempotent, open-world. The description goes well beyond that: the message 'can't be unsent,' who the sender address is and where replies land, what happens if no sender is configured, and the exact refusal conditions. This is the behavioral context an agent needs before a mutation.

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 core action and targeting rule are front-loaded, and every sentence carries distinct information (sender routing, refusal rules, confirmation requirement). It is dense and slightly long, but nothing is redundant 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 no output schema, the description still covers the error path ('it says where to connect Gmail') and the irreversible-mutation caveat. For a 5-parameter, no-output-schema send tool, an agent has what it needs to call it correctly.

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 only 40%, and the description compensates by explaining contact_id (start or continue a thread), conversation_id (target an existing thread), and subject's optional/reply-reuse behavior with 'Re:'. channel and body are largely left to the schema, so it is strong but not fully compensatory.

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 with cardinality and scope: 'Send one email to one contact, in their conversation thread.' That distinguishes it from sibling senders (ghl_send_email, ghl_send_sms) and from crm_* read/update tools 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?

Explicitly routes between the two entry keys ('by conversation_id, or contact_id to start or continue that contact's thread') and names the alternative channel with its status ('channel is email; texting isn't connected yet'). It also states refusal conditions (no email, do-not-contact) and a prerequisite workflow (read the message back and get the owner's OK first).

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