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

Annotations already flag destructiveHint=true, idempotentHint=false and openWorldHint=true, but the description adds material context they cannot: that issued tokens stop working, and the mandatory two-step confirm handshake. It still omits permission requirements and whether the deletion is permanent/recoverable, so it is strong rather than exhaustive.

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?

Three short sentences, front-loaded with the effect of deletion, then the procedural rule. Nothing is repeated and no filler appears.

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 two-parameter destructive tool with no output schema, the description covers impact, the confirmation protocol, and the shape of the first response (CONFIRMATION_REQUIRED plus confirmToken) — everything an agent needs to invoke it correctly.

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 both parameters are documented in-schema, including the confirmToken staging rule. The description restates the same first-call/second-call sequencing without adding new meaning such as token lifetime or where clientId originates beyond 'From list_oauth_clients.'

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 ('Delete an OAuth app the user registered') and adds the consequence ('the tokens it issued stop working'), which separates it cleanly from update_oauth_client, submit_oauth_client_for_review and list_oauth_clients in the sibling list.

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?

Gives a clear procedural context: the first call yields CONFIRMATION_REQUIRED, the agent must tell the user what will happen, then re-call with identical arguments plus confirmToken. It does not name alternatives (e.g. update vs delete) or state prerequisites like app ownership, so it stops short of full when/when-not guidance.

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