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

Annotations already say non-read-only, non-idempotent, non-destructive. The description adds the key behavioral fact beyond them: the alert is 'real', i.e. it actually delivers a notification to a live destination, which is why the guard clause exists. It stops short of saying whether prior alerts are affected or what the response looks like.

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?

Two short sentences, action first then the safety constraint. Nothing wasted and no ambiguity.

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-parameter action tool with annotations covering the safety profile, this covers the essentials. The only real gap is sourcing destination_id, which is implied by 'existing' but not directed to a sibling listing tool.

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 0%, so the description must compensate. 'Existing destination' clarifies that the ID must reference a pre-created destination, but it doesn't say where to obtain that ID (e.g. list_alert_destinations) or the expected format.

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 real test alert to an existing destination.' That is clearly distinct from list/page destination siblings, though the description never names those siblings explicitly.

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?

'Run only when the user asked to send the test' is an explicit when-to-use gate that prevents unsolicited test alerts. It does not mention alternatives such as list_alert_destinations for finding a destination, but the core exclusion is stated.

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