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

Annotations cover the safety profile (readOnlyHint, openWorldHint), so the bar is lower, and the description adds genuinely useful non-structured context: a $0.005 USDC per-call cost via x402. It also lists the returned fields. It stops short of addressing pagination behavior (limit/offset) or rate limits.

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?

Two sentences, front-loaded with the purpose and filter list, then the return shape and cost. Dense but every clause maps to a distinct filter or behavioral fact; the parenthetical '(or new in the last N days)' is the only slightly redundant bit since the schema already documents new_in_days.

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?

No output schema exists and the description compensates by naming the returned fields (number, name, address, SIC codes, dates), plus it discloses cost. For a 10-parameter tool the only real gap is pagination/ordering semantics for limit and offset, which matters for lead-list use.

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?

With 70% schema coverage the schema carries much of the load, but the description adds meaning by grouping filters conceptually (name contains, location, SIC codes, incorporation date range or 'new in last N days', status, type) and clarifying the date-range/new-in-days relationship. Limit/offset remain unexplained, so not a 5.

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 clear verb+resource ('Search UK companies') and enumerates the filter dimensions, so an agent knows exactly what the tool retrieves. It doesn't name or contrast with siblings such as uk_company, uk_filings, or company_registry, which is the one thing keeping it from a 5.

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 phrase 'for lead lists and market maps' implies the intended use case, which is more than nothing. However there is no explicit when-to-use/when-not guidance and no routing away from single-entity siblings like uk_company or uk_kyb, so the agent must infer the selection boundary.

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