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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds genuinely non-obvious behavior: the collision case returns already-exists and leaves the key unchanged, and creation auto-generates one translation per configured locale from the default-locale source text. It does not explain why the operation is flagged destructive or whether generated translations overwrite anything, leaving a small gap.

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 tight sentences: trigger, behavior/return, and exclusion. The most decision-relevant information (when to use it and what it returns) is front-loaded with no 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?

Return values are covered by an output schema and the safety profile by annotations, so the description's remaining job is trigger conditions and edge behavior — both supplied via the already-exists no-op rule. An agent has everything needed to call this 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 description coverage is 100%, so every parameter (key length, model default, value default, context, project) is already documented in the schema. The description restates the value/model semantics at a high level ("source text in the default locale") without adding syntax or format detail, so the baseline 3 applies.

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+resource (add a string/key to translations) and summarizes the return payload: the created key plus one machine translation per configured locale. It is clearly distinguishable from update_phrase and delete_phrase, and the sibling set confirms this is the creation path.

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?

"Use this when someone asks to add a new string or key" gives a clear trigger condition, and "Not for changing an existing translation" supplies an explicit exclusion. It stops short of naming update_phrase as the alternative for that case, so the routing is implied rather than stated.

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