Skip to main content
Glama

Verified Handles

by org.verifiedhandles
OverviewDiscussionsAdmin

Search entries

search_entries
Read-only

Search the entries as the site search does: words match titles, subtitles and descriptions; a Wikidata QID finds the entries linked to it; a VHID finds that entry and the entries that link to it.

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes
offsetNo

Output Schema

NameRequiredDescriptionDefault
limitNoThe page size used: the `limit` asked for, clamped to the endpoint’s range.
queryYesThe query as it was read: trimmed and cut to 100 characters.
totalYesHow many entries matched in all.
offsetNoThe offset used: the `offset` asked for, clamped to 0–10,000.
resultsYesBest match first.
next_offsetNoThe `offset` of the next page, or null when this is the last one. Follow it rather than computing it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedOutput schema / properties / results / items / properties / claimed
      Added value: +{
+  "description": "The person or organisation the entry is about has claimed it. Never who.",
+  "type": "boolean"
+}
    • addedOutput schema / properties / results / items / properties / entity_kind
      Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "person",
+        "musical_group",
+        "sports_organization",
+        "broadcaster",
+        "publisher",
+        "educational_institution",
+        "research_organization",
+        "religious_organization",
+        "museum",
+        "financial_institution",
+        "chain",
+        "nonprofit",
+        "company",
+        "organization",
+        "show",
+        "website",
+        "software",
+        "brand"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "The finer kind of thing it is, from its Wikidata item’s classes; null when unknown (an organisation or a brand not yet read since kinds were added reads null until the sync next reads its item). Each kind belongs to one `entity_type`, and `person`, `organization` and `brand` are also the kinds of an entry of that type with no finer one. The kinds, with their type: `person` (person: person), `musical_group` (organization: musical group), `sports_organization` (organization: sports organisation), `broadcaster` (organization: broadcaster), `publisher` (organization: publisher), `educational_institution` (organization: educational institution), `research_organization` (organization: research organisation), `religious_organization` (organization: religious organisation), `museum` (organization: museum), `financial_institution` (organization: financial institution), `chain` (organization: retail or hospitality chain), `nonprofit` (organization: charity or non-profit), `company` (organization: company), `organization` (organization: organisation), `show` (brand: show), `website` (brand: website or app), `software` (brand: software), `brand` (brand: brand). New kinds may be added; treat an unknown value as its `entity_type`."
+}
    • addedOutput schema / properties / results / items / properties / thumb
      Added value: +{
+  "description": "The lead image at the width a list row draws it (100 CSS pixels), as a path on the site: the width the image is really served at (200 for a Commons picture), never one that redirects. Null when there is no image.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • changedOutput schema / properties / results / items / required
      Previous value: -[
-  "vhid",
-  "short",
-  "title",
-  "subtitle",
-  "verified",
-  "snippet",
-  "highlighted",
-  "url"
-]New value: +[
+  "vhid",
+  "short",
+  "title",
+  "subtitle",
+  "verified",
+  "claimed",
+  "entity_kind",
+  "thumb",
+  "snippet",
+  "highlighted",
+  "url"
+]
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully explains matching behavior (QID resolves linked entries; VHID returns the entry plus its backlinkers), which is real added context. It says nothing about result ordering, pagination behaviour, or caps, which is a gap but not a contradiction.

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?

A single front-loaded sentence that opens with the search metaphor, then enumerates the three matching modes in a compact colon-separated list. Dense but every clause carries distinct meaning; no filler.

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

Completeness4/5

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

For a read-only search with an output schema already defining return shape, the description covers the essential matching semantics an agent needs. The remaining gap is pagination (limit/offset behaviour), which matters given the hard caps but is minor relative to what is supplied.

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

Parameters3/5

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

Schema description coverage is 0%, so the description carries the burden, and it does explain "query" thoroughly across all three input forms. However, limit and offset are documented nowhere — neither the 50-item cap nor the 10000 offset ceiling — leaving two of three parameters opaque.

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

Purpose4/5

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

A specific verb plus resource ("search the entries") whose three matching modes — free text over titles/subtitles/descriptions, Wikidata QID, and VHID — clearly separate it from lookup siblings like get_entry or find_by_handle. It stops short of naming an alternative outright, but the semantics are unmistakable.

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 clause "as the site search does" plus the three query modes tells an agent exactly which input shapes are valid and therefore when this tool applies. It never states when to prefer get_entry, get_entries, or find_by_handle instead, so there is no exclusion guidance.

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

All Verified Handles toolsInspect
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.

Resources