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

Annotations declare a non-read-only, non-destructive, open-world call, and the description adds substantive context beyond them: no incident or score change, a once-per-minute rate limit, owner-only authorization, and the confirm=true gate that makes an omitted confirmation a no-op. These are exactly the behavioral facts an agent cannot infer from the annotations.

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 purpose is front-loaded in the first sentence, followed by constraints and the confirmation requirement in four tight sentences. Every clause carries actionable information with no 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?

For a state-adjacent, confirm-gated action with an output schema, the description covers side effects, rate limits, auth, the confirmation flow, and even points at output fields ('delivered and receiver_status'). Nothing needed to call it correctly is missing.

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 carry parameter meaning. It explains confirm thoroughly ('omitted confirmation performs no action'), but agent_id and api_key are left entirely to their schema titles, which is a real gap at 0% coverage.

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 description states a specific verb and resource: 'Send one signed incident.test to your configured webhook.' It is clearly distinct from siblings like agent_webhook_secret (which manages credentials) and the inbox tools, but it never names an alternative to differentiate itself 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?

It gives concrete operating conditions: 'Owner-only, once/minute', 'Inspect delivered and receiver_status; do not automatically replay', and 'Requires confirm=true after reviewing the effect'. The do-not-replay and confirmation guidance is strong, though it stops short of naming sibling alternatives an agent might confuse it with.

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