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

Goes well beyond the readOnly/idempotent/non-destructive annotations: privacy handling (applicant names only for organisations, addresses reduced to country, mark images never stored), the 52-issue rolling window, and the cost model (1 credit/call with a key, otherwise a 5-row preview at 20 calls/day). These are exactly the operational traits an agent needs and none are in the schema or 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?

A single dense paragraph that front-loads what the tool is, then coverage, privacy, and cost. Every sentence carries information, though the run-on field enumeration makes it slightly harder to scan than it could be.

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 a 23-param, no-output-schema query tool, it covers provenance, coverage window, privacy caveats, filter logic, and cost/pagination limits, and it lists the returned fields in lieu of an output schema. The missing piece is per-filter syntax for the many unlisted parameters.

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 0% across 23 params, so the description must compensate. It explains q ('searches all text fields') and that filters combine with AND, and its field list implicitly maps to many params (mark_text, classes, applicant_country, filing/publication dates, journal_number). But syntax and scope for the remaining filters (origin, section, applicant_type, class_count_min/max) remain undocumented, so compensation is only partial.

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+resource: 'Every UK trade mark application and international registration designating the UK accepted and published in the Intellectual Property Office's weekly Trade Marks Journal,' then enumerates the fields returned. It is immediately distinguishable from siblings like query_uk_companies or query_uk_insolvency by its domain and source publication.

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 operational context: rolling 52 weekly issues, a change feed for each week's new publications, AND-combining filters, and the q full-text behavior. It hints at the get_changes alternative but does not explicitly name it or state when to prefer one over the other, so it falls short of a 5.

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