Skip to main content
Glama

Search the Graunt catalog

search
Read-only

Search Graunt's catalog of evaluated data from many sellers. Returns matching packets with their id, title, and public URL. Start here to find data, then read one with fetch. search_match.words says how the listings matched the query: ALL (every word, or a synonym of it), SOME (some of the words), WORD_START (words that start with the query's words), SIMILAR_TITLE (titles spelled like the query) or NONE (no listing). On SOME and WORD_START each listing names its matched_words. Each result's type is listing or pool, and search_match describes only listings. Pools use a separate keyword matcher over their public descriptions and data types. When no listing matches, next_steps.post_request_url opens a buyer request with the query filled in.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoOnly listings of this kind of data, read from their media kind or their files.
limitNoMax results; default 20, cap 50.
queryYesSearch keywords.
camera_viewNoOnly video listings shot from this camera view.
ai_generationNoKeep only packets whose seller declares this AI-generation extent: NONE (not AI-generated), PARTIAL or FULL. A seller declaration, not a Graunt finding. AI processing of real material (cleaning, labeling, transcribing, captioning, structuring) is not AI generation, and a packet that contains video declares NONE.
video_subjectNoOnly video listings whose footage shows this subject.
rights_public_useNoThe "Show it publicly" permission: NONE keeps only packets that grant no public use, including those that record no answer; EDITORIAL, PROMOTIONAL and COMMERCIAL keep only packets that grant exactly that use. The rights the seller declared on the listing, which Graunt records: a seller declaration, not a Graunt finding.
seller_credentialNoKeep only packets whose seller declares a credential: declared keeps listings whose seller declares at least one credential (a trade license, certification, business registration, membership or qualification); checked keeps those whose seller holds at least one that a Graunt operator checked against a registry. A seller declaration that Graunt records, never a Graunt finding, a score or a ranking input.
rights_license_familyNoKeep only packets whose seller names this license family. In order, the values stand for: Proprietary, CC0 (public domain), CC BY, CC BY-SA, CC BY-NC, CC BY-ND, CC BY-NC-SA, CC BY-NC-ND, MIT, Apache 2.0, BSD 2-clause, BSD 3-clause, GPL 3.0, LGPL 3.0, MPL 2.0, ODC-BY, ODbL, Public domain, U.S. Government work. The rights the seller declared on the listing, which Graunt records: a seller declaration, not a Graunt finding.
rights_training_allowedNotrue keeps only packets whose seller declares that AI models may be trained on them; false keeps only those whose seller declares they may not. The rights the seller declared on the listing, which Graunt records: a seller declaration, not a Graunt finding.
rights_sublicense_one_clientNoThe "Sublicensing to one client" permission: true keeps only packets a buyer may license for one client and pass the license through to that client; false keeps only those a buyer may not, including those that record no answer. The rights the seller declared on the listing, which Graunt records: a seller declaration, not a Graunt finding.

Output Schema

NameRequiredDescriptionDefault
resultsYes
next_stepsNoPresent only when no listing matches.
search_matchNoHow the listings matched the query. Present whenever a query was given.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"Only listings of this kind. video: video listings."New value: +"Only listings of this kind of data, read from their media kind or their files."
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "video"
      -]New value: +[
      +  "video",
      +  "audio",
      +  "images",
      +  "documents",
      +  "spreadsheets",
      +  "code"
      +]
  2. Changed4 schema fields changed
    • addedOutput schema / properties / next_steps
      Added value: +{
      +  "description": "Present only when no listing matches.",
      +  "properties": {
      +    "post_request_url": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "post_request_url"
      +  ],
      +  "type": "object"
      +}
    • addedOutput schema / properties / results / items / properties / matched_words
      Added value: +{
      +  "description": "The query's words this listing holds, on SOME and WORD_START only (at most 8). how: WORD (the word or a form of it), SYNONYM (as: the phrase from Graunt's synonym table the listing holds), WORD_START (a word in the listing starts with it).",
      +  "items": {
      +    "properties": {
      +      "as": {
      +        "type": "string"
      +      },
      +      "how": {
      +        "enum": [
      +          "WORD",
      +          "SYNONYM",
      +          "WORD_START"
      +        ],
      +        "type": "string"
      +      },
      +      "word": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "word",
      +      "how"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / results / items / properties / type
      Added value: +{
      +  "enum": [
      +    "listing",
      +    "pool"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / search_match
      Added value: +{
      +  "description": "How the listings matched the query. Present whenever a query was given.",
      +  "properties": {
      +    "applies_to": {
      +      "enum": [
      +        "listing"
      +      ],
      +      "type": "string"
      +    },
      +    "words": {
      +      "enum": [
      +        "ALL",
      +        "SOME",
      +        "WORD_START",
      +        "SIMILAR_TITLE",
      +        "NONE"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "applies_to",
      +    "words"
      +  ],
      +  "type": "object"
      +}
  3. Changed2 schema fields changed
    • addedInput schema / properties / rights_public_use
      Added value: +{
      +  "description": "The \"Show it publicly\" permission: NONE keeps only packets that grant no public use, including those that record no answer; EDITORIAL, PROMOTIONAL and COMMERCIAL keep only packets that grant exactly that use. The rights the seller declared on the listing, which Graunt records: a seller declaration, not a Graunt finding.",
      +  "enum": [
      +    "NONE",
      +    "EDITORIAL",
      +    "PROMOTIONAL",
      +    "COMMERCIAL"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / rights_sublicense_one_client
      Added value: +{
      +  "description": "The \"Sublicensing to one client\" permission: true keeps only packets a buyer may license for one client and pass the license through to that client; false keeps only those a buyer may not, including those that record no answer. The rights the seller declared on the listing, which Graunt records: a seller declaration, not a Graunt finding.",
      +  "type": "boolean"
      +}
  4. Changed1 schema field changed
    • addedInput schema / properties / seller_credential
      Added value: +{
      +  "description": "Keep only packets whose seller declares a credential: declared keeps listings whose seller declares at least one credential (a trade license, certification, business registration, membership or qualification); checked keeps those whose seller holds at least one that a Graunt operator checked against a registry. A seller declaration that Graunt records, never a Graunt finding, a score or a ranking input.",
      +  "enum": [
      +    "declared",
      +    "checked"
      +  ],
      +  "type": "string"
      +}
  5. Changed2 schema fields changed
    • addedInput schema / properties / rights_license_family
      Added value: +{
      +  "description": "Keep only packets whose seller names this license family. In order, the values stand for: Proprietary, CC0 (public domain), CC BY, CC BY-SA, CC BY-NC, CC BY-ND, CC BY-NC-SA, CC BY-NC-ND, MIT, Apache 2.0, BSD 2-clause, BSD 3-clause, GPL 3.0, LGPL 3.0, MPL 2.0, ODC-BY, ODbL, Public domain, U.S. Government work. The rights the seller declared on the listing, which Graunt records: a seller declaration, not a Graunt finding.",
      +  "enum": [
      +    "PROPRIETARY",
      +    "CC0",
      +    "CC_BY",
      +    "CC_BY_SA",
      +    "CC_BY_NC",
      +    "CC_BY_ND",
      +    "CC_BY_NC_SA",
      +    "CC_BY_NC_ND",
      +    "MIT",
      +    "APACHE_2_0",
      +    "BSD_2_CLAUSE",
      +    "BSD_3_CLAUSE",
      +    "GPL_3_0",
      +    "LGPL_3_0",
      +    "MPL_2_0",
      +    "ODC_BY",
      +    "ODC_ODBL",
      +    "PUBLIC_DOMAIN",
      +    "GOVERNMENT_WORK"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / rights_training_allowed
      Added value: +{
      +  "description": "true keeps only packets whose seller declares that AI models may be trained on them; false keeps only those whose seller declares they may not. The rights the seller declared on the listing, which Graunt records: a seller declaration, not a Graunt finding.",
      +  "type": "boolean"
      +}
  6. Changed1 schema field changed
    • changedInput schema / properties / ai_generation / description
      Previous value: -"Keep only packets whose seller declares this AI-generation extent: NONE (not AI-generated), PARTIAL or FULL. A seller declaration, not a Graunt finding."New value: +"Keep only packets whose seller declares this AI-generation extent: NONE (not AI-generated), PARTIAL or FULL. A seller declaration, not a Graunt finding. AI processing of real material (cleaning, labeling, transcribing, captioning, structuring) is not AI generation, and a packet that contains video declares NONE."
  7. Changed4 schema fields changed
    • addedInput schema / properties / ai_generation
      Added value: +{
      +  "description": "Keep only packets whose seller declares this AI-generation extent: NONE (not AI-generated), PARTIAL or FULL. A seller declaration, not a Graunt finding.",
      +  "enum": [
      +    "NONE",
      +    "PARTIAL",
      +    "FULL"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / camera_view
      Added value: +{
      +  "description": "Only video listings shot from this camera view.",
      +  "enum": [
      +    "FIRST_PERSON",
      +    "AERIAL_OR_DRONE",
      +    "VEHICLE_OR_DASHCAM",
      +    "FIXED_CAMERA",
      +    "OTHER"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / kind
      Added value: +{
      +  "description": "Only listings of this kind. video: video listings.",
      +  "enum": [
      +    "video"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / video_subject
      Added value: +{
      +  "description": "Only video listings whose footage shows this subject.",
      +  "enum": [
      +    "PEOPLE_TALKING",
      +    "PEOPLE_IN_ACTION",
      +    "PEOPLE_HANDLING_OBJECTS",
      +    "HOW_TO_AND_TASKS",
      +    "SPORTS_AND_FITNESS",
      +    "MUSIC_AND_PERFORMANCE",
      +    "ANIMALS",
      +    "NATURE",
      +    "CITIES_AND_BUILDINGS",
      +    "DRIVING_AND_TRANSPORTATION",
      +    "INDUSTRY_AND_WORK_SITES",
      +    "FOOD_AND_COOKING",
      +    "PRODUCTS_AND_RETAIL",
      +    "ANIMATION",
      +    "VIDEO_GAMES"
      +  ],
      +  "type": "string"
      +}
  8. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already establish a safe read (readOnlyHint true, destructiveHint false, openWorldHint true), and the description adds real substance beyond that: result types (listing vs pool), the fact that search_match applies only to listings and pools use a separate keyword matcher, and a no-match fallback. That is exactly the kind of behavioral context annotations cannot express.

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

Conciseness3/5

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

The opening two sentences are well front-loaded, but the middle portion enumerates search_match values and matched_words propagation, which is return-value detail an output schema already carries. It is dense but not wasteful in intent; still, a meaningful share of the text duplicates structured output documentation.

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?

With 11 parameters, an output schema, and safety annotations, the description supplies enough to call the tool correctly: it explains the query interpretation, the listing/pool split, and what happens on zero results. It does not discuss result ordering or pagination behavior beyond the schema's limit, which is a minor omission given how rich the rest of the definition is.

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 the baseline is 3, but the description adds meaning the schema does not: the query's words are matched individually and can match synonyms, which shapes how an agent should phrase the query. It does not elaborate on the many filter parameters, but those are already fully documented in the schema.

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?

"Search Graunt's catalog of evaluated data from many sellers" names a specific verb and resource, and the return shape (id, title, public URL) is stated upfront. It also routes away from the closest sibling by saying "then read one with fetch," so an agent can separate discovery from retrieval without opening either schema.

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

Usage Guidelines5/5

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

"Start here to find data, then read one with fetch" gives an explicit position in the workflow and names the alternative tool. The description also covers the fallback path when nothing matches (next_steps.post_request_url), so there is little left to infer about when and how to use it.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources