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

Adds value beyond annotations: ownership enforcement and soft-delete behavior. Annotations indicate non-destructive; description clarifies it's a deactivation, not deletion.

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 sentences, no redundancy, front-loaded with action and resource.

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?

Completely covers the tool's effect for a single-parameter tool with no output schema. Explains historical event availability.

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?

Single parameter 'id' with 100% schema coverage. Description adds context that id is returned by subscribe, aiding usage.

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?

Clearly states 'Cancel a subscription by id'—specific verb and resource. Distinguishes from siblings like subscribe and list_subscriptions.

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?

Mentions ownership enforcement and deactivation behavior, implying context for when to use recent_alerts. No explicit 'when not to use', but sufficient guidance.

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