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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, and the description adds substantial context beyond them: ADMIN-only auth requirement, routing-only behavior with test configuration and state untouched, external storage with the investigation service, and rejection of unknown channel IDs with no partial changes. These details fully align with the annotations and help the agent understand side effects and failure modes.

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 description is front-loaded with purpose and routing scope, then methodically covers parameter behavior, storage semantics, error handling, and the read alternative. Every sentence adds operational value for a tool with only two parameters but non-obvious inheritance and override semantics.

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 covers auth requirements, parameter behavior, storage ownership, error semantics, and the read-back tool. It gives the agent everything needed to invoke the tool correctly and interpret the outcome without needing a return schema.

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 100%, and the schema already documents channelIds as registry UUIDs with empty-list and omit semantics. The description adds useful clarification beyond the schema: these are registry channel UUIDs from list_alert_channels, not Slack channel ids, and it explains the inheritance precedence relative to the source-level default. That extra meaning justifies going above the baseline 3.

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: 'Replace where one API test's DOWN/UP alerts are delivered.' It immediately scopes the operation as routing-only and distinguishes it from configuration changes, while naming related tools like get_api_test_destinations and set_notification_destinations. This lets an agent separate it from sibling destination tools without opening schemas.

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 explicit when-to-use and when-not-to-use guidance: omit/null clears per-test routing so it inherits the tenant default, empty list turns alerts off, and a per-test setting outranks the source-level one. It names the relevant alternative (set_notification_destinations with source e2e-monitoring) and the read counterpart get_api_test_destinations.

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