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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent expects a state-changing action. The description adds valuable nuance by clarifying that this is not permanent deletion ('does not permanently delete data'), which prevents over-interpretation of destructiveHint. It also discloses the required auth scope and the policy constraint not to invent alternative paths—useful context beyond 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 description is compact and front-loaded: the one-line summary is immediately followed by the most important caveat (non-permanence), then scope and API mapping. Every sentence earns its place—there is no filler or repetition of schema content.

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 simple tool with one optional parameter and no output schema, the description covers safety (non-destructive nuance), auth scope, endpoint mapping, and usage constraints. The only slight gap is that 'the current app' is not fully defined in the description itself, though the parameter schema clarifies how to target a specific app in multi-app orgs.

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 description coverage is 100%: the only parameter `x_app_id` is fully documented in the schema with guidance on when to set it ('multi-app orgs'). The tool description itself adds no extra parameter-level detail, so it does not compensate beyond the schema. Baseline 3 is appropriate because the schema carries the semantic weight.

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 clearly states the action ('Deactivate an app') and the specific resource ('the current app'), and immediately adds a crucial distinction from deletion: 'This does not permanently delete data.' This differentiates it from sibling delete* tools (e.g., deleteApiKey, deleteTemplate) and clarifies the operation's intent. The mapping to operationId `deleteApp` and DELETE /manage-org/app reinforces the purpose.

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?

Provides clear context: it acts on 'the current app', requires scope `org:manage`, and points to the exact HTTP path. It also warns 'Do not invent other paths' and notes shared billing/rate limits. However, it does not explicitly say when to choose this tool over alternatives like updateApp or getApp, or describe when deactivation is preferable to other lifecycle operations.

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