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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that by committing to output behavior: every answer carries source, date of last check, and a not-legal-advice note. Pagination, result caps, and default result size remain undisclosed.

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 opening sentence front-loads what the tool returns before any filtering detail, and the sibling redirect lands at the end where it is actionable. It is dense with parenthetical enumerations, which makes it long, but nearly every clause carries information an agent needs; the one redundancy is repeating the status terms inside the filter list after defining them.

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 correctly compensates by stating what every answer includes (source, last-check date, legal disclaimer) and by explaining the status vocabulary. For a six-parameter, all-optional filter tool this is nearly complete; only result limits and default ordering are left unspecified.

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 baseline is 3, but the description genuinely extends the schema: it decodes the status enum (gilt = already applies, beschlossen = adopted with a later date, erwartet = expected, not yet adopted) and clarifies that regulation accepts free words such as "REACH", "CLP", "GPSR", "PPWR", "2023/1542". It also spells out the product-group vocabulary, which the schema only lists as bare ids.

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 and resource ("Lists duties on product documents in the EU") plus the originating system (ProofPass's deadline tracker) and enumerates the returned fields (title, start date, status, requirement, legal sources). It also names the sibling it is not ("For a filter by role use check_duties"), so an agent can route between them without opening either schema.

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?

Gives clear usage context by listing the available filter axes (regulation, product group, status, date range) and explicitly redirects role-based filtering to check_duties. It does not, however, distinguish itself from other plausible siblings like list_open_duties or list_documents_due, and gives no guidance on behavior when no filters are supplied.

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