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

Goes well beyond the annotations: it warns that the current target is replaced and that Weblate rejects a partial update lacking both target and state, states the plural-form/language count constraint, notes the commit happens on Weblate's normal schedule, and discloses the permission prerequisite for approval. These are real behavioral facts an agent cannot infer from readOnly/destructive/idempotent hints alone.

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 WRITE marker and the core action, then dense but purposeful detail on state, plurals, and commit timing. Every sentence carries information; the trailing PATCH endpoint is mildly extraneous but harmless.

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 three-parameter write with no output schema, the description covers mutation semantics, enum meanings, validation constraints, permission prerequisites, and commit behavior, while the annotations cover the safety profile. Nothing an agent needs to call 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 already 100%, so the baseline is 3; the description adds value on top by explaining that target must have a plural-form count matching the language and that state cannot be omitted (partial updates rejected). It does not add anything for unit_id beyond the schema, but the added semantics on the other two parameters are substantive.

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 'WRITE: set the translation of one string (replaces the current target)', naming a specific verb, resource, and the exact mutation it performs. This cleanly separates it from sibling proposal tools like weblate_add_suggestion or weblate_accept_suggestion without requiring the schema to be opened.

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 useful context on when each state value applies and that state 30 requires the review workflow and permission, but never names an alternative (e.g., when to suggest via weblate_add_suggestion instead of writing directly). Usage is implied rather than explicitly routed.

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