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

Annotations cover only the safety profile (destructive, idempotent, openWorld); the description adds substantial context beyond them: the RESTORE_SAFETY release created or reused, how to undo via safetyReleaseNumber, soft-deleted steps retaining message history and contact values, application variable values left untouched, and the assistant-lock refusal. This is exactly the deeper behavioral disclosure the annotations cannot provide.

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?

Front-loaded with the core action and its guarantees, and every clause carries operational information (safety release, soft deletes, publish semantics, lock, permission). It is dense but unbroken prose, which makes it harder to scan than it could be.

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?

No output schema exists, and the description compensates by naming the returned safetyReleaseNumber and its undo role. Permissions, refusal conditions, mutation scope, and the confirm-with-user requirement are all present, so an agent has everything needed to call this destructive tool safely.

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%, so the baseline is 3, but the description adds real meaning for publish by explaining what the default actually means operationally (nothing is promoted until deploy_application, unless publish=true). releaseId and applicationId are left to the schema, which already documents them well.

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 ('Put an earlier release back into the editor') and immediately scopes what is restored (every flow, step, menu, action and variable, under the same ids). This clearly separates it from siblings like deploy_application, list_releases, and update_application.

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?

Explicitly states default behavior (bots keep running until deploy_application), when to use publish=true (rollback of a broken publish), the refusal condition (AI assistant is changing the bot), the permission requirement, and the imperative to confirm with the user. Alternatives and preconditions are all named.

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