Which checkpoint would serve this, and why (no inference)

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

Annotations already declare readOnly, idempotent, and closed-world behavior, so safety is covered. The description adds a genuinely useful performance trait -- 'microseconds of work, no model download or forward pass' -- that an agent cannot get from the annotations.

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?

Three short sentences, front-loaded with the core action and then the cost/positioning rationale. No filler, though the final sentence could be tightened into the first.

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?

With an output schema present, return values need not be described, and annotations cover the safety profile. The description supplies purpose and cost context; only the meaning of the required 'state' payload is left entirely to 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%, so the schema already documents lang ('force the language branch'), model, state, and questions. The description adds nothing about parameter syntax or interaction, which is acceptable at full coverage but not additive.

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 specific verb and resource: 'detect language/script and workflow, and name the checkpoint that fits.' The 'no model download or forward pass' framing implicitly separates it from the inference-based siblings (decide, decide_yes_no), though no sibling is named explicitly.

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?

It gives a positional hint -- 'useful before deciding whether a request needs the multilingual checkpoint at all' -- which implies this is a pre-flight step ahead of a decide-family call. However, no alternative tool is named and no when-not condition is given, so the routing guidance stays implicit.

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