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

The annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the description correctly spends its words elsewhere: it states the hard semantic limit ('says whether a code is well formed, never whether it was issued or belongs to a product') and confirms no persistence ('Nothing is stored'). That scope boundary is the single most important thing an agent could get wrong here, and the description disposes of it in one clause.

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, each doing distinct work: what is checked, how to supply input, and what the answer does not mean. The most load-bearing constraint (format-only, not issuance) is placed before the storage note, and there is no boilerplate or repetition of the title.

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 no output schema, the description carries the burden of describing results, and it does so at the level of meaning ('says whether a code is well formed') rather than shape — an agent knows what it will learn but not how per-code verdicts are structured in the response. Given the tool's low complexity (two flat parameters, one enum, no nesting), this is close to complete; only the answer's granularity is left 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?

Schema coverage is 100%, so the schema already carries the parameter documentation and baseline 3 applies. The description nonetheless adds real meaning beyond the schema by specifying that multiple codes can be supplied and that semicolons are an accepted separator — a detail not stated in the 'codes' property, whose example uses newlines only.

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 opens with a specific verb and resource ('Checks the check digit of identifiers') and enumerates exactly which identifier families are supported (UFI, CAS, EC, GTIN/EAN), so an agent can match it to a task without opening the schema. It stops short of explicitly contrasting itself with adjacent check_* siblings such as check_sds_structure or check_gpsr_information, but the enumeration of code types does the practical differentiating work.

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?

'Identifiers found on data sheets and labels' hints at the context of use, and the input-format sentence ('one code per line or separated by semicolons') tells the agent how to batch. However, there is no explicit when-to-use or when-not-to-use statement, and no pointer to alternative tools if the agent actually needs issuance/ownership verification rather than format checking — that exclusion is only implied by the 'never whether it was issued' caveat.

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