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

Annotations already declare write/destructive/open-world, but the description adds real context beyond them: the 'WRITE:' prefix, the fact that suggest is the default and is non-destructive, and that background returns a task url. It does not fully clarify overwrite/irreversibility of the translate mode, but the mode semantics are a meaningful addition.

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-loads the critical 'WRITE:' signal and the two source options before diving into per-parameter detail, so the most important selection cue comes first. It is dense but each clause carries information; the trailing POST endpoint is a minor but harmless addition.

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 9-parameter mutation tool with no output schema, the description covers the branching behavior, defaults and the background return (task url) well enough to invoke correctly. It leaves only the exact response shape of the synchronous path implicit.

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?

With 100% schema coverage the baseline is 3, and the description genuinely exceeds it by restating defaults and behavior for auto_source, mode, q (default state:<translated) and threshold (default 80), including the engines dependency for mt. It reinforces rather than merely repeats the schema.

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 ('fill a translation automatically') plus the two source strategies (others vs mt), which cleanly separates it from weblate_update_translation, weblate_add_suggestion and weblate_accept_suggestion. An agent can tell this is the batch auto-translation tool without opening the 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?

Explains how each mode behaves (suggest only adds suggestions, translate writes, fuzzy marks needing edit) and when to use background ('schedule a task instead of waiting'), giving clear operational context. It stops short of naming a sibling alternative or stating when NOT to use this tool versus manual editing.

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