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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the bar is lower. The description adds two genuine behavioral facts: cursor-based pagination behavior and a legal attribution obligation (Source: Aleva, CC BY 4.0) that constrains how results may be displayed. It does not cover data freshness or scope of the sweep, which keeps it from a 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?

Front-loaded with purpose, then pagination, then fields, then attribution — a sensible order. The field enumeration is long but earns its place because there is no output schema. Minor redundancy with the input schema's own descriptions.

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 9 optional filters, no output schema, and no required params, the description correctly compensates by enumerating returned columns and explaining pagination and attribution. What it omits is interpretive context — what a 'sweep month' means, where the data comes from, and how this differs from sibling web_* tools.

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 every filter, including equals vs any-of semantics and the se/nu domain. The description's field list largely restates column meanings already implied by the schema (e.g. 'se or nu', 'e.g. shopify'). It adds no filter interaction guidance, so baseline 3 applies.

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 names a specific resource domain (Swedish agentic commerce / UCP records) and says it 'returns a list of records', so the verb+resource is roughly inferable. However, the opening line is essentially the title restated, and it never distinguishes itself from close siblings like web_agents, web_mcp_registry, or web_mcp_servers. The field list hints at scope but the core purpose remains vague.

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?

There is no statement of when to use this tool versus alternatives, no prerequisites, and no exclusions, despite several overlapping web_* siblings. The only usage-adjacent instruction is pagination mechanics ('pass next_cursor to get the next page'), which is about how to call it, not when.

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