UK Data: UK Parliament committees

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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint false, openWorldHint), so the description focuses on useful extras: results are ordered newest first, every witness is expanded with role and organisation, and each item carries transcript links rather than content. It also discloses provenance (UK Parliament Committees API) and cost (1 credit), which the annotations do not. Return-shape is described at a summary level but paging behaviour beyond 'take' is left to the schema.

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 purpose, return contents, and example questions are front-loaded in the first two sentences, with exclusions, provenance, and cost trailing as compact parentheticals. Every clause carries information; nothing is repeated from the schema or annotations.

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 two-parameter read-only list tool with no output schema, the description adequately conveys what is returned and what is not, plus cost and source. The one residual gap is paging/volume behaviour when a committee has many sessions, which the description never touches and is only inferable from the 'take' schema field.

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% and both parameters are already documented, including the example '15x = Treasury Committee' and the take range/default. The description adds no syntax, format, or edge-case meaning for these parameters beyond restating that a committee id is needed, so the baseline of 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?

States a specific verb and resource ('List a committee's oral evidence sessions') and then enumerates exactly what comes back: meeting date, inquiry, every witness with role and organisation, and transcript links. It also marks its boundaries against adjacent resources ('Gives transcript links, not the transcript text or video'), so an agent can tell it apart from a transcript-fetching or bill-tracking sibling without opening the 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?

Supplies two concrete question shapes it answers ('when did the CEO give evidence', 'who has the committee questioned on X') and points to committee_search as the source of the required committee id, which effectively names a prerequisite tool. It does not give an explicit when-not rule or name a sibling to use for the transcript body beyond the negative 'not the transcript text or video'.

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, open-world and non-destructive behavior, and the description adds genuinely non-structured facts: the upstream source (UK Parliament Committees API), the 1-credit cost, and the name-only search limitation. It omits result ordering and how partial matches are handled.

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 verb, resource and return payload, then the routing role, then the scope caveat, then cost. Each sentence adds distinct information with no 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?

With no output schema, the description usefully enumerates the returned fields (id, house, type, parent committee, sub-committees, contact details), which is exactly what an agent needs to chain into follow-on tools. Only match/pagination behavior is left implicit.

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 both q and take are already documented, and the description adds only light reinforcement ('by name', what fields come back) with no syntax or matching-behavior detail beyond the schema. 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?

States a specific verb and resource ('Find a UK Parliament committee by name') plus the returned fields, and draws an explicit boundary against topic-based search: 'Searches committee names only, not inquiry topics.' That boundary is what distinguishes it from siblings like committee_evidence_sessions.

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?

Explicitly positions the tool as 'the first step for the other committee tools' and gives the answerable questions ('which committee covers X', 'how do I contact it'). It does not name the specific follow-on tool or state what to do if name search fails, so it stops just short of full routing 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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description does not need to restate that. It adds real value beyond the annotations by citing the upstream source (UK Parliament Oral Questions and Motions API) and disclosing a cost of 1 credit, which no structured field conveys.

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 sentences, each doing distinct work: what it returns, who cares, and where to go for detail, with the cost tag appended. Purpose is front-loaded and nothing is repeated from the schema.

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 no output schema, the description compensates by naming the returned fields, and it identifies the data source and credit cost. The only modest gap is that it does not characterise ordering/recency semantics (how 'most recent' is determined) or pagination.

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% for the single 'take' parameter, including the 1-100 range and the default of 20. The description adds no additional meaning about how many motions to request or how ordering/defaults behave, so the baseline 3 is appropriate.

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 — 'List the most recently tabled early day motions (EDMs) in the House of Commons' — and enumerates the fields returned (title, primary sponsor, date, supporter count). It is clearly distinguishable from the sibling early_day_motion_detail, which is explicitly named for the deeper view.

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 names the alternative tool and the condition that selects it: 'For full text and the list of signatories use early_day_motion_detail.' That gives an agent a clear routing rule, though it does not say when this recent-list tool is inappropriate (e.g., historical or topic-specific searching).

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 traits, and the description adds value beyond them: the upstream source (UK Parliament Oral Questions and Motions API), the Commons-only scope restriction, and the explicit exclusion of answers. The '1 credit' cost note is genuinely useful operational context. It stops short of describing 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-loaded with the core verb and resource, then scope limitations and cost. The single long opening sentence is dense but every clause carries real information; nothing is redundant.

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 no output schema, the description usefully enumerates what comes back (asker, answering department and minister, question text, topical questions), which is the key missing structured data. It omits ordering and whether historical dates are supported, a minor gap for a three-parameter list tool.

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 all three parameters are already documented in the schema and the baseline of 3 applies. The description only loosely anchors 'from a given date' to from_date and adds no meaning for take or to_date beyond what the schema states.

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: 'List House of Commons oral questions tabled for answer at departmental question time', and enumerates the returned facets (asker, department, minister, question text, topical questions). It also draws a hard boundary against Hansard replies, so an agent can distinguish it from the written-question siblings without opening a 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?

Provides a concrete use-case question ('what will MPs ask at Home Office questions this week?') and an explicit exclusion ('lists questions, not what was said in reply'). It does not, however, name the written-question siblings (e.g. written_question_search, unanswered_written_questions) as alternatives, so routing between oral and written questions is left implicit.

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 non-destructive, so the safety bar is met. The description adds real value beyond them: default ordering (most recently tabled first), the fields surfaced (department due to answer, due date), the upstream source (Commons and Lords), and a 1-credit cost. It omits volume/pagination behaviour, which is the only notable behavioural gap.

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 definition, then scope, audience and source in descending importance; no sentence is redundant. The credit-cost note is a useful operational aside rather than filler, though the audience sentence could be trimmed without loss.

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 one-optional-parameter, read-only, output-schema-less list tool, the description covers what is returned, in what order, from which source, and clarifies a likely misinterpretation (lateness). An agent has everything needed to call it correctly and interpret the result.

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?

There is a single optional parameter (take) with 100% schema description coverage, so the schema already documents the 1-100 range and default of 20. The description does not mention page size or a cap, adding no meaning beyond the schema; 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?

States a specific verb and resource ("List UK parliamentary written questions") plus a precise scope qualifier ("still waiting for a government answer") that separates it from written_question_search and written_question_detail. The ordering and returned fields are also named, so an agent can identify the tool without opening the 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 a clear use context ("useful for public affairs teams tracking what departments have been asked") and a scope exclusion ("it does not judge whether a department is late"), which prevents misuse for lateness monitoring. It does not name the sibling tools that would cover answered questions or detail lookups, so routing is implied rather than explicit.

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, non-destructive and openWorld, so the safety profile is covered. The description adds genuine context beyond that: the returned components (question and answer text, asker/answerer, dates, holding vs corrected answer, attachments), the upstream API, and a cost of 1 credit. It stops short of describing failure behavior for invalid or missing ids.

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?

Purpose and id source are front-loaded in the first clause, and the return contents follow in a compact list. The id-vs-UIN warning and cost note are somewhat duplicative of structured fields, so it is efficient but not maximally lean.

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 one parameter, no output schema, and safety fully covered by annotations, the description usefully enumerates what comes back, which is the main gap it needed to fill. Only minor gaps remain, such as how attachments are represented or what happens on an invalid id.

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% and the single id parameter already documents 'int, required, written question id ... not the UIN'. The description repeats that same id-vs-UIN distinction rather than adding new syntax or format meaning, so the schema is doing the heavy lifting and 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?

States a specific verb and resource: get one UK parliamentary written question including the government's full answer. It distinguishes itself from written_question_search (the id source) and from adjacent siblings like unanswered_written_questions, so an agent can select it without opening the 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?

Clearly frames this as a follow-up lookup whose id comes from written_question_search, and explicitly excludes UIN-based lookup, which is the most likely mistake. It does not spell out a when-not-to-use case (e.g., bulk retrieval), but the routing context is clear.

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 read-only, idempotent, open-world behavior, so the safety profile is covered. The description adds genuinely non-redundant context: the response fields (asker, answering department, dates, status), that answers are returned as an excerpt rather than full text, the upstream data source, and a per-call credit cost. Pagination/result-cap behavior is left implicit, 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?

Four tight sentences, front-loaded with purpose followed by return shape, routing, and cost. The potholes/NHS/visa examples earn their space by making the resource concrete, and nothing repeats the schema or annotations.

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 two-parameter read-only search with no output schema, the definition covers purpose, likely return fields, scope boundaries, sibling routing, and cost. Nothing an agent needs in order to call this correctly 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 both parameters are already documented, and the description adds little beyond confirming that 'q' is a keyword/phrase searched across both questions and answers. Baseline 3 applies; no syntax, quoting, or result-count guidance is offered beyond the schema.

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 ('Search UK parliamentary written questions and the government's answers by keyword') and immediately bounds the scope (Commons and Lords written questions). It explicitly distinguishes itself from written_question_detail and from oral questions/Hansard, so an agent can differentiate it from siblings without opening a 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?

Names concrete use cases ('what a department has said about potholes, NHS waiting lists or visa numbers') and gives an explicit routing rule: use written_question_detail for full answer text, and note that oral questions and Hansard debates are out of scope. That covers when-to-use, when-not-to-use, and the alternative in one pass.

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 readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful context beyond them: the upstream source (UK Parliament Written Statements API, Commons and Lords) and a credit cost of 1 per call. It discloses no pagination or result-cap behaviour, so it lands just above the annotated baseline rather than well above it.

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?

Four sentences, front-loaded with purpose and scope and finished with a compact cost tag; nothing is padded. The one nod to extra length is the explanatory aside about what ministers use statements for, which does earn its place by sharpening disambiguation.

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 no output schema, the description compensates by enumerating return fields (title, minister and role, department, date, House, excerpt), plus source and cost. What remains unstated is result ordering, pagination and whether an empty keyword is permitted — minor gaps for a two-parameter search tool.

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% with only two parameters, so the schema already documents both q and take. The description reinforces keyword search ('by keyword'), which maps to q, but says nothing about the take parameter, the 1-100 range, or the default of 10. Baseline 3 applies where the schema carries the load.

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) and resource (UK ministerial written statements) and immediately explains what a written statement is, so an agent understands the content type without prior knowledge. The exclusions of oral statements and press releases carve it cleanly away from sibling tools such as oral_questions_upcoming and news_search.

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 a clear positive context (formal ministerial announcements of policy changes, data updates, decisions) and explicit negative scope (no oral statements in the chamber, no press releases). It stops short of naming any sibling tool as the alternative, so routing is inferred rather than directed.

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