tool_check_translation

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

With no annotations, the description carries the full burden and does so well: it discloses the exact failure mode (string-only files silently leave dialogue untranslated), the runtime-error risk of duplicate old strings, and what it scans for. It does not state whether the check is read-only/local, but for a project-analysis tool that is a minor omission.

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 one-line purpose and the headline bug, then the detail. The middle 'most important check' paragraph is somewhat verbose but every clause adds diagnostic value; nothing is pure 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?

Although there is no output schema and no annotations, the description explicitly documents the return dict shape ({ok, source_language, languages:[...]}) and issue severities. Combined with complete parameter docs, an agent has everything needed to call and interpret it.

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 0%, so the description must compensate, and it does: it specifies that project_path is an absolute path to the Ren'Py project root and that language is a language code whose None value triggers checking all languages under game/tl/. Both parameters and the default behavior are fully explained.

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 ('Deep-check translation coverage') and immediately narrows it with the concrete class of bug it catches. It is clearly distinguishable from sibling list/lint tools like tool_list_translations, which merely enumerate rather than diagnose.

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?

The description establishes a clear context ('Deep-check' vs the lighter tool_list_translations implied sibling) and explains why it matters (silent bugs left in source language). It does not explicitly name when to prefer it over tool_check_language_picker or tool_check_project, so exclusion guidance is inferred rather than stated.

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