UK Legal Research

Search Committee Evidence

committees_search_evidence

Read-onlyIdempotent

USE THIS TOOL WHEN you have a committee_id and want the oral and written evidence submitted to it.

Returns ONE PAGE of evidence (default 20) plus total, the source's count of matching items. evidence_type='both' lists all oral evidence first, then all written evidence, each newest-published first as the source orders it. Free-text titles are capped per max_title_chars; witness lists are capped at 10 per item. An organisation witness (no named individual) is rendered as ' ()'; a null entry means the source gave no name for that witness at all. For committees with many submissions, re-call with offset=offset+returned while has_more is true.

Authoritative source for parliamentary committee evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum evidence items to return. Default 20. For evidence_type='both' a page may hold only oral, only written, or the last oral items followed by the first written items.
`offset`	No	Number of evidence items to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true. For evidence_type='both' this is a position in the combined sequence (all oral evidence, then all written evidence).
`committee_id`	Yes	Committee ID from committees_search_committees results.
`evidence_type`	No	Type of evidence to search.	both
`max_title_chars`	No	Per-item cap on the free-text title field. Default 300 prevents context blow-up from verbose inquiry titles. Raise to 1000+ only when you need the full title text.

Output Schema

TableJSON Schema

Name	Required	Description
`limit`	Yes	Max evidence items requested for this page
`total`	Yes	Evidence items matching this query, from committees-api's totalResults (for evidence_type='both', the oral count plus the written count)
`offset`	Yes	Number of evidence items skipped before this page
`evidence`	No	Evidence items in this page. Titles are capped per max_title_chars; witness lists are capped at 10 per item.
`has_more`	Yes	True if evidence exists beyond this page (offset + returned < total). Re-call with offset=offset+returned to fetch the next page.
`returned`	Yes	Number of evidence items actually returned in this call
`committee_id`	Yes	Committee ID this page belongs to
`evidence_type`	Yes	Evidence type filter applied to this query

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedSep 14, 2026

changedInput schema / properties / limit / description

Previous value: -"Maximum evidence items to return. Default 20. When evidence_type='both' the limit is split across oral and written (roughly half each)."New value: +"Maximum evidence items to return. Default 20. For evidence_type='both' a page may hold only oral, only written, or the last oral items followed by the first written items."

changedInput schema / properties / offset / description

Previous value: -"Number of evidence items to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true."New value: +"Number of evidence items to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true. For evidence_type='both' this is a position in the combined sequence (all oral evidence, then all written evidence)."

changedInput schema / properties / offset / maximum
```
Previous value: -2000New value: +2147483647
```

changedOutput schema / description

Previous value: -"A page of evidence submissions to a parliamentary committee.\n\nReturned by committees_search_evidence. Callers paginate by\nre-calling with offset=offset+returned while has_more is True.\nWhen evidence_type=\"both\", oral and written evidence are\ninterleaved in a single `evidence` list and the limit is split\nacross both."New value: +"A page of evidence submissions to a parliamentary committee.\n\nReturned by committees_search_evidence. Callers paginate by\nre-calling with offset=offset+returned while has_more is True.\nWhen evidence_type=\"both\", the sequence being paged is all oral\nevidence followed by all written evidence."

changedOutput schema / properties / has_more / description

Previous value: -"True if there may be more evidence beyond this page. Re-call with offset=offset+returned to fetch the next page. Conservative: when evidence_type='both', True if either oral or written upstream page came back full."New value: +"True if evidence exists beyond this page (offset + returned < total). Re-call with offset=offset+returned to fetch the next page."

addedOutput schema / properties / total

Added value: +{
+  "description": "Evidence items matching this query, from committees-api's totalResults (for evidence_type='both', the oral count plus the written count)",
+  "type": "integer"
+}

changedOutput schema / required

Previous value: -[
-  "committee_id",
-  "evidence_type",
-  "offset",
-  "limit",
-  "returned",
-  "has_more"
-]New value: +[
+  "committee_id",
+  "evidence_type",
+  "offset",
+  "limit",
+  "returned",
+  "total",
+  "has_more"
+]

Changed2 schema fields changedSep 13, 2026

changedOutput schema / properties / evidence / items / properties / witnesses / anyOf

Previous value: -[
-  {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / evidence / items / properties / witnesses / description

Previous value: -"Witness names (oral evidence only, capped at 10 per item)"New value: +"Witness display names (oral evidence only, capped at 10 per item). An organisation witness (e.g. a regulator or company giving evidence collectively, not through one named individual) has no personal name upstream — that entry is rendered as '<Organisation> (<Role>)' instead, e.g. 'Bank of England (Governor)'. A null entry means committees-api.parliament.uk supplied neither a personal name nor an organisation for that witness slot — honest absence, not a fabricated placeholder; it is not omitted from the list, so the count of entries still matches the number of witnesses upstream."

Changed7 schema fields changedJun 14, 2026

addedInput schema / properties / committee_id

Added value: +{
+  "description": "Committee ID from committees_search_committees results.",
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / evidence_type

Added value: +{
+  "default": "both",
+  "description": "Type of evidence to search.",
+  "enum": [
+    "oral",
+    "written",
+    "both"
+  ],
+  "type": "string"
+}

addedInput schema / properties / limit

Added value: +{
+  "default": 20,
+  "description": "Maximum evidence items to return. Default 20. When evidence_type='both' the limit is split across oral and written (roughly half each).",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / max_title_chars

Added value: +{
+  "default": 300,
+  "description": "Per-item cap on the free-text title field. Default 300 prevents context blow-up from verbose inquiry titles. Raise to 1000+ only when you need the full title text.",
+  "maximum": 2000,
+  "minimum": 50,
+  "type": "integer"
+}

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "description": "Number of evidence items to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true.",
+  "maximum": 2000,
+  "minimum": 0,
+  "type": "integer"
+}

removedInput schema / properties / params

Removed value: -{
-  "additionalProperties": false,
-  "description": "CommitteeEvidenceInput.",
-  "properties": {
-    "committee_id": {
-      "description": "Committee ID from committees_search_committees results.",
-      "minimum": 1,
-      "type": "integer"
-    },
-    "evidence_type": {
-      "default": "both",
-      "description": "Type of evidence to search.",
-      "enum": [
-        "oral",
-        "written",
-        "both"
-      ],
-      "type": "string"
-    },
-    "limit": {
-      "default": 20,
-      "description": "Maximum evidence items to return. Default 20. When evidence_type='both' the limit is split across oral and written (roughly half each).",
-      "maximum": 100,
-      "minimum": 1,
-      "type": "integer"
-    },
-    "max_title_chars": {
-      "default": 300,
-      "description": "Per-item cap on the free-text title field. Default 300 prevents context blow-up from verbose inquiry titles. Raise to 1000+ only when you need the full title text.",
-      "maximum": 2000,
-      "minimum": 50,
-      "type": "integer"
-    },
-    "offset": {
-      "default": 0,
-      "description": "Number of evidence items to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true.",
-      "maximum": 2000,
-      "minimum": 0,
-      "type": "integer"
-    }
-  },
-  "required": [
-    "committee_id"
-  ],
-  "type": "object"
-}

changedInput schema / required

Previous value: -[
-  "params"
-]New value: +[
+  "committee_id"
+]

Changed1 schema field changedMay 30, 2026

changedInput schema / properties / params / description

Previous value: -"CommitteeEvidenceInput with committee_id, evidence_type,\noffset/limit pagination, and max_title_chars."New value: +"CommitteeEvidenceInput."

Changed1 schema field changedApr 20, 2026

addedInput schema / properties / params / description

Added value: +"CommitteeEvidenceInput with committee_id, evidence_type,\noffset/limit pagination, and max_title_chars."

Changed14 schema fields changedApr 15, 2026

addedInput schema / properties / params / properties / limit

Added value: +{
+  "default": 20,
+  "description": "Maximum evidence items to return. Default 20. When evidence_type='both' the limit is split across oral and written (roughly half each).",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / params / properties / max_title_chars

Added value: +{
+  "default": 300,
+  "description": "Per-item cap on the free-text title field. Default 300 prevents context blow-up from verbose inquiry titles. Raise to 1000+ only when you need the full title text.",
+  "maximum": 2000,
+  "minimum": 50,
+  "type": "integer"
+}

addedInput schema / properties / params / properties / offset

Added value: +{
+  "default": 0,
+  "description": "Number of evidence items to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true.",
+  "maximum": 2000,
+  "minimum": 0,
+  "type": "integer"
+}

changedOutput schema / description

Previous value: -"Generic wrapper for non-object return types."New value: +"A page of evidence submissions to a parliamentary committee.\n\nReturned by committees_search_evidence. Callers paginate by\nre-calling with offset=offset+returned while has_more is True.\nWhen evidence_type=\"both\", oral and written evidence are\ninterleaved in a single `evidence` list and the limit is split\nacross both."

addedOutput schema / properties / committee_id

Added value: +{
+  "description": "Committee ID this page belongs to",
+  "type": "integer"
+}

addedOutput schema / properties / evidence

Added value: +{
+  "description": "Evidence items in this page. Titles are capped per max_title_chars; witness lists are capped at 10 per item.",
+  "items": {
+    "properties": {
+      "date": {
+        "anyOf": [
+          {
+            "format": "date",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Date the evidence was given or submitted"
+      },
+      "id": {
+        "description": "Evidence item ID",
+        "type": "integer"
+      },
+      "title": {
+        "description": "Evidence title or session description (may be truncated per max_title_chars)",
+        "type": "string"
+      },
+      "type": {
+        "description": "Type of evidence",
+        "enum": [
+          "oral",
+          "written"
+        ],
+        "type": "string"
+      },
+      "url": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "URL to the evidence document"
+      },
+      "witnesses": {
+        "anyOf": [
+          {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Witness names (oral evidence only, capped at 10 per item)"
+      }
+    },
+    "required": [
+      "id",
+      "type",
+      "title"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / evidence_type

Added value: +{
+  "description": "Evidence type filter applied to this query",
+  "enum": [
+    "oral",
+    "written",
+    "both"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / has_more

Added value: +{
+  "description": "True if there may be more evidence beyond this page. Re-call with offset=offset+returned to fetch the next page. Conservative: when evidence_type='both', True if either oral or written upstream page came back full.",
+  "type": "boolean"
+}

addedOutput schema / properties / limit

Added value: +{
+  "description": "Max evidence items requested for this page",
+  "type": "integer"
+}

addedOutput schema / properties / offset

Added value: +{
+  "description": "Number of evidence items skipped before this page",
+  "type": "integer"
+}

removedOutput schema / properties / result

Removed value: -{
-  "type": "string"
-}

addedOutput schema / properties / returned

Added value: +{
+  "description": "Number of evidence items actually returned in this call",
+  "type": "integer"
+}

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "committee_id",
+  "evidence_type",
+  "offset",
+  "limit",
+  "returned",
+  "has_more"
+]

removedOutput schema / x-fastmcp-wrap-result
```
Removed value: -true
```

First observedApr 14, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint, so safety profile is covered. The description adds substantial behavioral context: pagination behavior (one page, has_more), ordering for evidence_type='both', caps on free-text titles and witness lists, rendering of organisation vs null witnesses, and the 'Authoritative source' note. This goes well beyond annotations and no contradiction exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the usage condition and then provides dense operational details. While it is relatively long, every sentence adds value (pagination, caps, rendering rules). The structure is logical—first when to use, then behavior. It could be trimmed slightly, but it is appropriately sized for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 parameters, pagination, ordering, caps, and witness rendering rules, and the description covers all these aspects. It mentions the return includes 'total' and explains pagination. Since an output schema exists, it need not fully describe return values. The description is complete enough for an agent to call the tool correctly without ambiguity, including hints for efficient pagination.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so each parameter is documented in the schema. The description adds meaning beyond the schema: it explains what 'both' means for evidence_type (oral first, then written), the purpose of max_title_chars (prevents context blow-up), and how offset works in the combined sequence. This enriches the raw schema definitions, so a score above the baseline of 3 is warranted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'USE THIS TOOL WHEN you have a committee_id and want the oral and written evidence submitted to it,' which states a specific verb (search/get), a specific resource (committee evidence), and a clear condition. It clearly distinguishes this tool from sibling tools like committees_get_committee (which retrieves committee details) and committees_search_committees (which searches committees) by focusing on evidence. The title 'Search Committee Evidence' reinforces the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives an explicit condition for use ('when you have a committee_id and want evidence') and details on pagination ('re-call with offset=offset+returned while has_more is true'). It implies alternatives by naming the exact scenario, but it does not explicitly state 'do not use for committee search' or mention sibling tools. The guidance on when to use is strong, but exclusion criteria are only implied, not stated.

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

All UK Legal Research tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.