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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the authorization requirement, that the override bypasses the AI pipeline, that it persists while the source is unchanged, and that any source edit invalidates it like other cached translations. This is exactly the mutation/lifecycle context an agent needs and cannot get from structured fields.

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 core action in the first clause, then layers authorization, pipeline bypass, invalidation, and the lang constraint, with essentially no filler. It is slightly run-on with several constraints chained in one paragraph, but every sentence carries information.

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-param write tool with no annotations and no output schema, the description covers authorization, lifecycle/invalidation, locale validity, and publication state, which is nearly everything needed to call it correctly. It stops short of stating upsert-vs-conflict behavior when an override already exists for the post/locale.

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 75%, so baseline is 3, and the description adds real value on top: lang must be one of the 8 site locales and must differ from the detected source language, a constraint absent from the schema, plus the published-post restriction tied to postId. postId itself (uuid) remains described only in name, keeping this short of a 5.

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+resource with scope ('Write a manual translation override for one post in a target locale'), which is clear and actionable. It never names the nearest sibling (mod_retranslate_post) or any other translation tool, so differentiation from alternatives is left implicit via the 'bypasses the AI pipeline' phrasing.

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?

Provides rich precondition context: admin or board-moderator authorization (boardless posts admin-only), only published posts can be overridden, and lang must differ from the detected source language. It does not explicitly contrast when to pick this over AI retranslation or admin_set_topic_translations, so exclusions relative to siblings are absent.

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