Log email activity

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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=true, and the description adds the genuinely useful behavioral fact that no email is dispatched. It is silent on consequences the annotations flag implicitly, such as what happens on repeated logging of the same email (non-idempotent duplicates) or whether logging triggers automations or associates with the given dealId/contactId.

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?

Short and front-loaded, with the critical "does not send" caveat in the second sentence. The opening fragment "Log email activity." merely restates the title before the real sentence begins, which is a small amount of dead weight.

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 single non-destructive write with a fully documented nested schema and no output schema, the essentials are covered. Missing are the return value / how to reference the logged activity afterwards and how duplicate or re-logged emails are handled, both of which an agent needs before invoking a non-idempotent create.

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 the nested body object documents from/to/cc/bcc/subject/content/emailSentAt/dealId/contactId individually, including the HTML-content note and the default-sent-time behavior. The description adds nothing 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?

States a specific verb and resource ("Logs an email activity") and immediately negates the most likely misreading with "This operation does not send the email." It does not name any of the adjacent siblings (list_email_activities, get_email_activity, delete_email_activity) for contrast, but the log-vs-send distinction is the one that matters here.

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?

"Use it to log emails that were sent by an external application or email client" gives a concrete selection condition: this is for recording activity that already happened elsewhere. It stops short of stating when not to use it (e.g. do not call to record an email this system sent, or to update an existing activity).

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