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

Annotations only declare the mutation profile; the description adds non-obvious behavior: the change propagates to every project sharing the string, marks the text human-edited, and returns previous plus new values. The cross-project propagation is exactly the kind of blast-radius detail annotations cannot convey.

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 short sentences: trigger, effects/return, exclusion. Front-loaded with the use case and free of repetition of schema or annotation content.

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?

Despite an output schema already existing, the description goes further by naming what is returned and the shared-project side effect. Prerequisites and scope are fully covered for a four-parameter mutation tool.

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 each parameter is documented in-schema (exact existing key, locale code, new text length bound), so the description carries no additional parameter detail. Baseline 3 applies when the schema does all the work.

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 and resource ('fix or change the text of one key in one language') and immediately scopes it against the sibling add_phrase with 'Not for adding a new key.' An agent can distinguish this from add_phrase/delete_phrase without opening a schema.

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?

Gives a clear triggering situation ('when someone asks to fix or change the text') and an explicit exclusion ('Not for adding a new key'). It stops short of naming add_phrase as the alternative tool by name, but the when/when-not framing is unambiguous.

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