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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds genuine value beyond them: it discloses the output shape ("returns it as a text block", important since no output schema exists) and that the scope is "formal completeness" only, not substantive verification, plus "Nothing is stored." It does not say what happens when information is missing or invalid, which keeps it below 5.

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?

A single front-loaded sentence: verb and legal basis first, the checked field list in parentheses, output form and the no-storage assurance at the end. Nothing is redundant or padding.

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 an 11-parameter validation tool with no output schema, the definition covers purpose, checked fields, and return type, but leaves the failure mode undefined — whether an incomplete record produces a list of gaps, an error, or a partially filled text block is unknown. The conditional responsible-person requirement is mentioned but the other non-Art. 19 fields (country, product, language, warnings) are not explained at all.

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 73% across 11 parameters, so the schema already carries most per-field meaning. The description does add one thing the schema lacks: the responsible person in the EU is conditional, required only "for manufacturers outside it" — meaningful conditional semantics. It says nothing about country, product, language, or warnings, so it only partly compensates for the remaining coverage gap.

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 ("Checks ... for formal completeness and returns it as a text block") tied to a named legal resource (Art. 19 GPSR information for an online offer) and enumerates the fields in scope: manufacturer, postal address, electronic address, product identifier, responsible person in the EU. That level of specificity separates it from the other check_* siblings (battery passport, duties, identifier codes, SDS structure) without needing to name them.

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 use case is implied rather than stated: an agent can infer "call this when you need to verify the formal completeness of an online consumer offer's GPSR data." There is no explicit when-to-use statement, no prerequisites, and no guidance on what to do with the result or which sibling to pick instead.

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