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

Annotations mark destructiveHint: true, but the description clarifies the reversible nature ('preserving its definition; republish any version later') and explicitly states it does not touch members. This adds transparency beyond the raw annotation and prevents misunderstanding.

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 succinct, using one sentence to convey the action, its effect, and exclusions, with no redundant or extraneous information. It is well-structured and easy to parse.

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?

The description provides sufficient context for a mutation tool: what it does, what it preserves, and what it does not affect. It lacks explicit mention of return values, but given the absence of an output schema, this is acceptable and not a critical gap.

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?

The sole parameter app_id is fully described as 'the app id to hide (last_published_version -> 0; definition preserved)', giving clear meaning and the exact effect on the resource. Schema coverage is 100% and the description reinforces it.

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 ('Hide an app'), specifies the effect (last_published_version -> 0), and explicitly notes what it does not do (preserve definition, not touch members). This is unambiguous and distinguishes it from destructive deletions.

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?

The description implies a use case (temporarily hiding an app while allowing republishing) but does not explicitly compare with alternatives like publish_app or delete_app. It does not directly state when to use this instead of a sibling tool, leaving some inference to the agent.

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