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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes beyond that by stating the deletion is permanent, affects every locale, and cascades to other projects that share the phrase. This gives the agent a clear understanding of the full destructive impact.

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?

Two sentences deliver the core action and the most important side-effect without filler. The destructive action is front-loaded, and the shared-phrase caveat is placed exactly where it adds value.

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 two-parameter destructive tool with a full input schema and an output schema, the description is complete. It explains scope, permanence, and the surprising shared-phrase side effect, so an agent has enough context 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 already have meaningful descriptions. The description reinforces that the key refers to one key's locale group but does not add parameter-level detail beyond what the schema provides.

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 uses a specific verb phrase, 'Permanently delete every locale translation for one key in a project,' and clearly identifies the resource and scope of the operation. It also distinguishes itself from less destructive phrase operations by explaining the shared-phrase cascade behavior.

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 clearly implies this is for permanently removing a key's translations, but it never explicitly names an alternative tool or states when not to use it. The phrase 'rather than only detaching the project' hints at a non-destructive alternative, but the agent is left to infer which sibling tool provides that behavior.

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