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

Annotations already declare destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: mail is sent from the org's configured address, template placeholders are interpolated from candidate and job-position data, and 'The email reaches the candidate' makes the real external delivery explicit. It omits failure behavior and the duplicate-send risk implied by non-idempotency.

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 the action and sender, then the mode split, then the delivery note. Little waste, though the closing sentence 'The email reaches the candidate' largely restates what 'send an email' already conveys.

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?

No output schema exists, so the description carries the burden of explaining outcome, and it does so minimally by asserting real delivery. For a six-parameter mutation with a side effect outside the system, it is adequate, though it says nothing about what happens on invalid templates or whether a record of the sent email is retained.

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 the schema already explains all six parameters, making 3 the baseline. The description adds some meaning by framing subject/body as mutually exclusive with templateId/templateName and by explaining that {{variables}} are filled from the candidate and job position, which implicitly justifies jobDescriptionId.

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 and resource ('Send an email to a candidate') plus the sending identity ('organization's configured email address'), and the second sentence enumerates the two supported modes (free-form vs. template). It does not explicitly contrast itself with siblings such as list_contact_templates (for discovering template IDs) or add_candidate_note (for internal notes), so it stops short of a 5.

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?

The description signals a conditional usage split ('either a free-form subject and body, or an email template'), which tells the agent two paths exist. However, it gives no guidance on when to prefer one over the other, no prerequisite (e.g., resolve a template via list_contact_templates first), and no exclusions for internal-only communication.

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