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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explains the purpose and the source-code proximity criterion, but it does not disclose key behavioral traits such as whether storing relationships overwrites existing ones, whether it is idempotent, or what permissions are required. This lack of operational detail is a significant gap for a mutating tool.

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 concise at two sentences, front-loaded with the core action, and every sentence earns its place. It states the purpose, the benefit (more consistent translations), and the usage heuristic without unnecessary filler.

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 tool is relatively simple with three parameters and no output schema. The description covers its purpose and usage context well, but it lacks behavioral details such as overwrite semantics or whether a call returns a job ID. Given the absence of annotations and output schema, the description is reasonably complete but leaves important operational questions unanswered.

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 already provides complete descriptions for all three parameters, achieving 100% coverage. The description adds conceptual value by defining the semantics of 'related keys' (keys appearing near each other in source code), which goes beyond the schema's 'List of related keys in order'. This extra context helps the agent understand the intent behind relatedKeysInOrder.

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 identifies the action ('Store key relationships') and the resource ('key relationships for Tolgee machine translation'), with a specific purpose: using related keys as context for more consistent translations. This distinguishes it from sibling tools like create_keys or get_key, which focus on individual key management.

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 provides a clear usage heuristic: keys that appear near each other in source code should be stored as related. This gives the agent contextual guidance on when to invoke the tool, though it does not explicitly state when not to use it or mention alternatives. The 'should be stored as related' phrasing implies the appropriate scenario.

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