uk-parliament-mcp-server

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, lowering the disclosure burden. The description adds useful behavior beyond those annotations: collection selectors paginate whole records, overview omits publications, publications reveal supplied legislation.gov.uk statute links, and contentCursor reconstructs oversized records.

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?

The description is front-loaded with the core retrieval purpose and every clause carries a selection, dependency, or pagination rule. It is dense and semicolon-heavy, which makes it harder to scan, but there is little obvious filler.

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?

This is a complex 10-parameter tool with an output schema and annotations. The description supplies the critical cross-parameter dependencies, collection filtering limits, publication nuance, and oversized-record recovery needed to invoke it correctly.

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 coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning beyond the schema. It links billStageId to section=stages, itemId to the parent collection for singular amendment/motion retrieval, and restricts amendment filters to the amendments collection.

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 states a specific verb and resource: retrieve a Westminster bill overview or selected sections including stages, publications, amendments, and motions. It enumerates the selectable sections, so an agent can understand the tool's scope without opening the schema, and it is not a tautology of the title.

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 gives clear conditional guidance for selecting sections, including that stage/amendment/motion selections require billStageId and singular selections also require itemId. It also explains filtering and pagination rules, though it does not explicitly route the agent from ukparl_search_bills to this retrieval tool beyond the schema's billId note.

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

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.

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

Beyond the read-only/idempotent annotations, the description discloses important behavior: voting uses native 20-row pages, reports lobby and teller facts, and omits lifetime participation metrics. It also explains cursor continuation rules and the existence of contentCursor for reconstructing oversized records.

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?

The description is dense but front-loaded and every clause carries operational meaning. It is somewhat semicolon-heavy and could be easier to scan, but it does not waste words.

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 seven-parameter tool with an output schema and rich annotations, the description covers all critical caller decisions: section selection, house applicability, role categories, cursor handling, and voting pagination. Nothing essential is missing for correct invocation.

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?

Although schema coverage is already 100%, the description adds cross-parameter semantics: house is required for interests/voting, category applies only to roles, and cursor continuation requires unchanged selectors. It also clarifies that voting pagination is independent of the limit parameter and that committee person IDs differ from member IDs.

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 gives a specific verb and resource: retrieving a member profile and its subsections (roles, committee seats, contact, interests, voting). It clearly distinguishes the tool from list/search siblings by requiring a member ID and by enumerating member-specific subsections.

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 gives clear usage conditions: interests and voting require an explicit House, and roles need a category to page whole biography collections. It does not explicitly mention when to use this instead of ukparl_search_members, but the get-vs-search distinction is clear from the description.

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

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

Annotations already declare readOnly/idempotent/openWorld, so the description's value-add is the cursor lifecycle: 'Follow opaque collection cursors with the same filters; use contentCursor to reconstruct an oversized selected payload.' That explains pagination and reconstruction behavior beyond structured fields. It stops short of describing return shape, but the output schema covers that.

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 compact sentences, front-loaded with the core 'resolve/inspect before searching' purpose, then behavior. The phrase 'or a named reference topic for filter IDs' is slightly opaque, but overall there is little waste.

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 6 parameters, full schema coverage, an output schema, and read-only annotations, the description covers the missing behavioral layer (cursor/reconstruction semantics). It is complete enough to invoke correctly, with only minor ambiguity around reference topics.

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 coverage is 100%, so baseline is 3, but the description adds operational meaning to the cursors: cursor requires repeating the same normalized filters, and contentCursor reconstructs an oversized payload. That is genuine meaning beyond the schema's one-line parameter descriptions, justifying a bump.

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 first sentence states a specific verb+resource pair ('Resolve Parliament filter IDs and inspect source coverage') and positions the tool as a pre-search reference, which distinguishes it from the sibling search/get tools. It is clear what the tool does, though the dense enumeration in the second sentence muddies the core purpose slightly.

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 description explicitly frames usage as 'before searching' and maps topic choices to situations ('identifiers for ID namespaces and required selectors, coverage for Hansard date limitations, or a named reference topic for filter IDs'). This gives an agent clear selection context, though there are no explicit when-not-to-use exclusions.

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

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

Annotations already cover read-only, idempotent and open-world semantics. The description adds real operational context beyond them: no implicit session/date scoping, cursor continuation must retain filters, and contentCursor is a lossless same-selection continuation. It does not cover output shape, but an output schema exists.

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 the core purpose, then routes to siblings, then caveats. Dense but each sentence carries information; there is minor redundancy (department/answering-body distinction appears twice) but nothing wasteful.

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 15-parameter, all-optional search with a full output schema and safety annotations already present, the description supplies what's missing: sibling routing, the absence of implicit scoping, and pagination/oversized-item handling. An agent has enough to call it correctly.

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 coverage is 100%, so the baseline is 3, but the description adds cross-field meaning: department IDs are distinct from answering-body IDs, inAmendableStage=false means unrestricted (not 'non-amendable'), and originatingHouse omission includes all. Some of this duplicates schema text, but the clarifications genuinely reduce misuse.

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 ('Search') on a specific resource ('Westminster bill summaries') and enumerates the filterable dimensions (title, house, session, sponsor, department, stage, type, status). It explicitly distinguishes itself from ukparl_get_bill (full records) and ukparl_lookup_reference (ID resolution), so an agent can route without opening schemas.

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 explicit routing: use ukparl_lookup_reference for stage/type/department IDs and ukparl_get_bill for complete records. It also states that no session/date scope is inferred, how to follow collection cursors (preserve filters), and how contentCursor reconstructs oversized items — concrete when/when-not guidance.

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

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

Annotations already declare readOnly/idempotent/openWorld, so the bar is lower, yet the description adds real semantic caveats: 'not_recorded means only the source list, never abstention', party totals count non-tellers and tellers separately from headline counts, and detail preserves teller identities. It does not cover error behavior or cross-House mismatch consequences, 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-loads the search case correctly and has no filler, but it is a single semicolon-chained run-on that packs mode routing, caveats, and cursor rules together, making it harder to parse than a short bulleted structure would be. Terms like 'roster selectors' and 'memberVote' are introduced without explanation.

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 12-parameter, 4-mode tool with an output schema, the description covers mode selection, required divisionId, cursor vs contentCursor distinction, and data-interpretation quirks across all modes. Nothing essential for correct invocation is missing.

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 coverage is 100%, so baseline is 3; the description still adds meaning by tying memberId results to memberVote with the recorded lobby and teller flag, clarifying party is an exact source label 'not a party ID', and explaining that divisionId must come from the same House. That is genuine value beyond the schema text.

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 ('Search official Commons or Lords division summaries') and enumerates the four operation modes (search, detail, voters, party_totals). The resource noun (division summaries) implicitly separates it from siblings like search_hansard or search_bills, though no sibling is named explicitly.

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 per-mode routing: text/date/member filtering for search, and 'use detail, voters or party_totals with a divisionId from the same House'. Also states the operational rules for cursors ('Follow collection cursors with unchanged filters'). No explicit when-not-to-use or named alternatives among the ukparl_* siblings.

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

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

Goes well beyond the readOnly/openWorld/idempotent annotations by disclosing that full contribution text including HTML is returned, that previews are labelled summaries, that debateSectionId does not yield a whole debate transcript, and that historical coverage has a 2004–2006 gap. It also specifies cursor disciplines (collection cursor unchanged, contentCursor for lossless oversized contributions), which is exactly the operational detail annotations cannot convey.

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?

The core purpose lands in the first sentence and each subsequent sentence carries distinct information with no filler. The final sentence packs cursor and retry rules together, which is dense but still readable, so it falls just short of ideal structure.

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 9-parameter, zero-required search tool with an output schema and full annotation coverage, the description supplies the remaining essentials: archive completeness caveats, sibling routing for coverage questions, pagination/continuation rules, and result-shape expectations. Nothing an agent needs in order to call it correctly appears to be missing.

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 coverage is 100%, so the baseline is 3, but the description adds real semantics on top: it explains how cursor must be replayed with identical filters, what contentCursor is for, and how debateSectionId is used across repeated calls. Date-window narrowing on retry also gives practical meaning to startDate/endDate.

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 plus resource (search spoken Westminster Hansard contributions) and enumerates the available facets (topic, member, House, date, debateSectionId). The word 'spoken' cleanly separates it from siblings like ukparl_search_questions and ukparl_search_divisions without the agent needing to open another schema.

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 concrete operating guidance: repeat with a returned debateSectionId to drill into a section, consult ukparl_lookup_reference topic=coverage for archive questions, and retry timeouts with shorter date windows. It doesn't explicitly state when to prefer a sibling such as ukparl_search_questions over this tool, which keeps it 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.

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

Annotations already establish readOnly, idempotent, and openWorld behavior, so the description's job is to add call-specific behavior. It does so by noting that results preserve latest profile fields, that cursor continuation requires unchanged filters, and that contentCursor handles oversized records. Those are valuable operational details beyond the annotations, though it could say more about result ordering or partial-match 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?

Three dense sentences, front-loaded with the core purpose and immediately followed by the two most consequential parameter behaviors and the retrieval alternative. No sentence is filler.

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?

Annotations cover safety and an output schema exists, so the description need not explain return values. It still covers the operational edges an agent needs: historical queries, cursor stability, oversized records, and the handoff to ukparl_get_member.

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 100%, the baseline is 3. The description restates the asOf restriction and cursor invariants that the schema already documents for those parameters, adding little new semantic detail beyond consolidation.

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 opens with a specific verb and resource ('Find MPs and peers') and enumerates the searchable dimensions. It also explicitly names the retrieval sibling ukparl_get_member, so an agent can distinguish search from fetch without inspecting schemas.

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 states when to use this tool versus ukparl_get_member ('retrieve sections with ukparl_get_member') and gives explicit behavioral rules for currentOnly, asOf, and cursor reuse. The asOf exclusion ('accepts name only, without House, party or location filters') tells the agent exactly how to avoid an invalid combination.

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

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

Annotations already declare readOnly/idempotent/openWorld, and the description adds real behavior beyond them: search spans all sessions and includes withdrawn questions, undated UIN lookups are ambiguous and return multiple candidates, and contentCursor exists for lossless oversized answers. It does not discuss error behavior or result ordering, but the scope and cursor semantics are meaningful disclosures.

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 and facets, then moom into mode/UIN and cursor rules with no filler sentences. Dense but each clause carries an operational instruction; slightly packed, with four distinct rules in the middle sentence.

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?

Given 16 optional parameters, two modes, an output schema and complex cursor/pagination behavior, the description covers what an agent needs: how to pick a mode, how to disambiguate UINs, how to handle paging, and where to get full content. Output format details are correctly left to the 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?

With 100% schema coverage the baseline is 3, but the description adds semantics the schema alone does not convey: the UIN/questionId distinction, that a UIN never determines House, and that answeringMemberId is independent of memberId. Cursor handling (follow collection cursors unchanged, use contentCursor for oversized answers) further clarifies two of the parameters.

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?

Names a specific verb and resource ('Search Westminster written questions and answer previews') and enumerates the searchable facets: text, UIN, asking/answering member, House, answering body, answer state and dates. It also distinguishes the detail mode, which separates it from the pure search siblings like ukparl_search_hansard.

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 explicit operational guidance: an undated UIN returns candidates across sessions, so narrow with tabling dates; switch to mode=detail with a returned questionId for full HTML, corrections and attachments. It also states the exclusion rule that a UIN is not a questionId and never determines House, and gives cursor handling instructions.

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