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

Annotations cover the safety profile (destructiveHint=true, openWorldHint=true, idempotentHint=false), but the description adds substantial context beyond them: the sender address (noreply@send16.com), the visible banner, the sample merge values ('Test'), and a specific failure mode (403 SENDING_PAUSED with the reassurance that nothing was sent and to contact support). That is exactly the behavioral detail an agent cannot get from structured fields.

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 the core action, then layers the deliverability details and the error path. Five sentences is longer than minimal, but each one carries load-bearing information (sender identity, consent rule, refusal handling), so little is wasted.

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 mutation tool with no output schema, the description adequately covers outcome expectations (what the recipient sees), the safety gate (own address, confirm first), and the failure branch (403 SENDING_PAUSED). An agent has everything needed to call it correctly and handle refusal.

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 all three parameters (email, apiKey, templateId) are already documented in the schema. The description adds only that the target is 'one email address' and refers to a 'saved workspace template', which is helpful but does not exceed what the schema provides. 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 ('Send a preview of a saved workspace template to one email address') and the goal ('so the user can see it in a real inbox'). This clearly distinguishes it from the sibling send_campaign_test and send_email, which target campaigns/general mail rather than a saved template.

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 usage constraints: 'Only send to the user's own address unless they ask otherwise' and 'Confirm the test address with the user first.' This tells the agent both when to use it and how to gate the call, with no inference required.

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