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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, and the description adds genuinely new context: Blind Mode means person fields and notice text are never ingested, AND-combination of filters, 1 credit per call with an API key, and an unauthenticated preview of 5 rows at 20 calls/day. That cost and rate-limit disclosure is material. It stops short of describing result ordering or pagination behavior.

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-loads the resource and source before the qualifiers, and every clause carries information. The em-dash enumeration is dense but scannable; the pricing clause is slightly crammed into the same breath as behavioral notes but still earns its place.

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 and no annotations describing return values, yet the description never sketches the shape of a notice record or pagination metadata. Given 8 undocumented parameters and a credit-metered call, an agent lacks enough to construct a precise query without guessing field formats.

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 schema description coverage at 0% and 8 parameters, the description carries the full burden but only clarifies `q` (searches all text fields) and that filters are ANDed. `company`, `notice_code`, `notice_type`, `published_at_after/before`, `page` and `per_page` are left entirely undocumented, including accepted formats or whether notice_code is an enum-like code.

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 (corporate insolvency notices from The Gazette, the official UK public record) and enumerates the notice categories returned — winding-up petitions/orders, appointments, moratoria, creditor notices. The 'company-level facts only' scope clause plus the named source cleanly separates it from siblings like query_uk_companies or query_uk_charities.

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?

It explains filter behavior ('Filters combine with AND; q searches all text fields') and the cost/preview model, which helps an agent decide whether to call it. But it never states when to prefer this over adjacent datasets or when it is not appropriate, so usage is implied rather than directed.

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