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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered. The description adds real behavior beyond that: cursors must be followed with unchanged filters, contentCursor retrieves oversized records losslessly (and must be drained before advancing the collection cursor), memberships retain all role periods, and no document text is extracted. It does not discuss failure modes or error semantics for invalid ID/namespace combinations, but the added context is substantial.

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 well — the search-then-detail workflow leads — and every sentence is factual. But it is one undifferentiated paragraph of ten terse clauses with jargon (isInquiry, sourcePath, contentCursor) strung together, making it hard to scan for the mode an agent actually needs; the closing sentence about sourcePath is low-value density for most calls.

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 20 parameters across 9 modes with an output schema present, the description covers the routing, cursor discipline, ID namespaces, and scope exclusions an agent needs to invoke it correctly. Remaining gaps (rate limits, invalid-combination errors, expected empty results) are minor given full schema coverage and an output schema.

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 baseline is 3; the description earns above that by explaining parameter interdependencies the schema does not state as relationships — that evidenceId and evidenceType must be in the same namespace, that businessId is required for inquiry/evidence but merely an optional publication filter, and that personId is not the Members API memberId. It still leaves the evidenceType effect on evidence listing slightly implicit.

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?

Opens with a specific verb+resource ("Find Westminster committees") and immediately enumerates the multi-mode surface: detail, members, inquiries, publications, evidence. An agent can tell what the tool does and that it is a committee-scoped hub, and it is implicitly distinct from the bill/member/division siblings. It stops short of an explicit sibling differentiation statement (e.g., "for member biographies use ukparl_get_member instead of mode=members").

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 dominant usage decision for this tool is which mode to pick, and the description routes every one of them: mode=search to find, committeeId for detail/members/inquiries/publications, businessId+mode=inquiry for business detail, publicationId+mode=publication for report metadata, mode=evidence with businessId and evidenceType, mode=evidence_detail requiring evidenceId plus matching evidenceType. It also states a clear when-not ("No document downloads or text extraction") and a cross-API warning (personId vs Members API memberId).

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