Machine translations awaiting review

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

readOnlyHint is already declared, and the description partially repeats it, but it adds genuinely new behavioral context: there is no approve capability by design, so an agent must not attempt state changes here. It also describes what each returned item contains (source text plus provider output), which shapes how the agent presents results. Some of the rationale prose is more editorial than operational.

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?

The core purpose is front-loaded in the first sentence, followed by useful constraints. The closing clause 'deliberately not a tool here and never will be' is slightly emphatic but earns its place by preventing an agent from searching for an approve tool.

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?

An output schema exists, so return values need not be spelled out, yet the description helpfully signals the shape of each item. With annotations covering the read-only profile, the definition is complete enough to call correctly. It could note the default scope (all locales) at the description level, but that is in the schema.

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 description coverage is 100% and both parameters (root, locales) are documented there. The description adds no meaning to root or locales — it never mentions locale filtering, defaults, or what root scoping implies. Baseline 3 is correct when the schema carries the parameter burden.

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?

The description states a precise resource and scope: machine translations still awaiting human review, each with source text and provider output. An agent can distinguish this listing tool from verbaly_write_drafts or verbaly_translate without opening a schema. It does not name a sibling tool explicitly, which keeps it just short of a 5.

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?

Usage context is clear (read-only inspection of pending drafts) and there is an explicit negative guideline: approving is not and will never be a tool here, it must go through `verbaly review --approve` by a human. That exclusion is strong guidance. The remaining gap is that it never contrasts itself with the sibling tools (e.g. verbaly_write_drafts) that populate this list.

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