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

Even though the destructiveHint annotation already marks this as a destructive operation, the description goes further by stating that submission records are anchored to the source form, are not deleted, and that historical reports fall back to the source text. This is exactly the kind of behavioral consequence an agent needs before calling a delete operation.

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 sentences no unnecessary words. The main action appears immediately, followed by the two most important side-effect insights, then a constraint. Everything is structured for fast parsing by an agent.

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 covers the purpose, the exact scope (per-language translation), the side-effect safety guarantee (submissions not deleted), the report fallback behavior, and the primary-language restriction. With the input schema and output schema present, nothing relevant to correct invocation is missing.

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 schema covers both parameters with 100% coverage, so a baseline of 3 is appropriate. The description adds additional meaning by clarifying that the 'language' parameter must be a non-primary translation language, which is important selection guidance beyond the bare enum 'Which language version to delete.'

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 opens with a precise action-verb and resource: 'Delete one language version (translation) of a form.' That clearly identifies what the tool does and naturally sets it apart from deleting an entire form. The final sentence reinforces the boundary by noting the primary language is not affected by this operation.

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 gives a clear intended use—deleting a translation language—and explicitly warns that the primary language cannot be removed through this tool. It does not name sibling alternatives like 'delete_form' when a full form deletion is intended, so a small routing gap remains.

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