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

Annotations declare destructiveHint=true, but the description goes well beyond them: it spells out that the write overwrites the existing translation and goes live in the next download/CDN release, that a translator's value is only a candidate, that no placeholder/plural/length validation runs, that the source language cannot be written, and that the caller should inspect the reply's `stored` field. This is exactly the extra behavioral context the 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?

Front-loaded with the operation type and scope, then layered with role semantics, validation gaps, and the endpoint. Dense but each clause carries information; the trailing raw endpoint path is the only near-filler, and the whole thing is a single efficient paragraph.

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 4-parameter write tool with no output schema, the description covers the mutation effect, who it affects, what validation is skipped, and where to look for the result (`stored`). Nothing an agent needs to invoke it correctly 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic constraints on top: values are 'stored as-is, with no placeholder, plural or length check' and the source language cannot be targeted via `lang`. These are behavioral facts about the parameters that the schema alone does not state.

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?

Opens with a specific verb+resource+scope: 'set the translation of ONE source key in ONE target language'. The 'WRITE:' prefix and the single-key/single-language scoping distinguish it from siblings like localazy_translate_with_ai or localazy_import_keys without needing to open their schemas.

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?

Explains the role-dependent outcome clearly: reviewers/managers/owners/trusted translators write live, a plain translator's value becomes a pending candidate. That is strong context for predicting effect, but it never explicitly names an alternative tool or states when not to use this one (e.g., bulk translation via localazy_translate_with_ai).

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