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

The description adds substantial behavioral context beyond the annotations: it states the fail-closed behavior even if read-back fails, notes that the server will submit nothing for that user afterward, and explains that unauthenticated calls are refused before any read. This goes well beyond the destructive and idempotent hints already present.

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?

Every sentence earns its place: the core operation, fail-closed consequence, argument alternatives, authentication requirement, and schema note are all necessary and front-loaded. The description is dense but not bloated.

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 destructive, server-to-server revocation tool, the description covers invocation paths, authentication, side effects, fail-closed behavior, and the intentionally permissive schema. With an output schema present, return-value documentation is not needed, and nothing essential to calling the tool 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?

Although the input schema is empty and permissive, the description fully compensates by defining the two mutually exclusive argument sets: accessToken, or userId plus support_reason. It also clarifies authentication is via header, not arguments, and that strict validation occurs after authentication.

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 opens with a specific verb and resource: 'Revoke the end user's delegation from Otto's side' and 'confirm by read-back.' It clearly identifies the action and its effect, distinguishing this revocation operation from read-only or status tools like otto_delegation_status.

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 usage paths and context: the user path with accessToken versus the support path with userId and support_reason, plus server-to-server-only authentication via the x-otto-delegation-auth header. It does not explicitly name sibling alternatives or state when not to use this tool, so it stops short of full alternative routing.

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