Skip to main content
Glama

Dblp Search Publications

dblp_search_publications
Read-onlyIdempotent

Search the dblp computer science bibliography (about 10 million papers, articles, theses and proceedings) from a stored copy of the publisher's CC0 bulk release. Matches words in the title, author names, venue and year; a title or an author name typed as a phrase is matched as a phrase first ("attention is all you need", "Yoshua Bengio"). Results are newest first within each match class. Every answer carries data_as_of, answered_from and the licence. Default 30 results, max 100.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "deep learning neural networks"
    },
    "name": "dblp_search_publications"
  }
}

Input Schema

NameRequiredDescriptionDefault
hitsNoResults per page, 1-100 (default 30)
firstNo0-based offset (default 0)
queryYesTitle words, an author name, a venue or a year, e.g. "attention is all you need" or "Yoshua Bengio"

Output Schema

NameRequiredDescriptionDefault
hitsNo
countNoHits in this response
firstNo0-based offset of the first hit
queryNo
totalNoTotal matches; null when not counted
sourceNo
licenceNo
messageNoPresent on a zero-hit answer
data_as_ofNoDate of the dblp release the stored copy was built from
total_noteNoPresent when the total is not counted
answered_fromNoWhere the answer came from (stored copy)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changed
    • addedOutput schema / properties / answered_from
      Added value: +{
      +  "description": "Where the answer came from (stored copy)",
      +  "type": "string"
      +}
    • addedOutput schema / properties / count
      Added value: +{
      +  "description": "Hits in this response",
      +  "type": "number"
      +}
    • addedOutput schema / properties / data_as_of
      Added value: +{
      +  "description": "Date of the dblp release the stored copy was built from",
      +  "type": "string"
      +}
    • addedOutput schema / properties / first
      Added value: +{
      +  "description": "0-based offset of the first hit",
      +  "type": "number"
      +}
    • addedOutput schema / properties / hits
      Added value: +{
      +  "items": {
      +    "properties": {
      +      "authors": {
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      },
      +      "key": {
      +        "description": "dblp record key",
      +        "type": "string"
      +      },
      +      "link": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "pages": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "title": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "type": {
      +        "type": "string"
      +      },
      +      "venue": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "volume": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "year": {
      +        "type": [
      +          "number",
      +          "null"
      +        ]
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / licence
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / message
      Added value: +{
      +  "description": "Present on a zero-hit answer",
      +  "type": "string"
      +}
    • addedOutput schema / properties / query
      Added value: +{
      +  "type": "string"
      +}
    • removedOutput schema / properties / result
      Removed value: -{
      -  "properties": {
      -    "completed": {
      -      "description": "Completion timestamp",
      -      "type": "number"
      -    },
      -    "hit": {
      -      "description": "Array of publication results",
      -      "items": {
      -        "properties": {
      -          "authors": {
      -            "description": "Author information",
      -            "properties": {
      -              "author": {
      -                "description": "Author(s) name(s)",
      -                "type": [
      -                  "array",
      -                  "object"
      -                ]
      -              }
      -            },
      -            "type": "object"
      -          },
      -          "doi": {
      -            "description": "DOI identifier",
      -            "type": "string"
      -          },
      -          "ee": {
      -            "description": "Electronic edition URL",
      -            "type": "string"
      -          },
      -          "info": {
      -            "description": "Publication info string",
      -            "type": "string"
      -          },
      -          "title": {
      -            "description": "Publication title",
      -            "type": "string"
      -          },
      -          "type": {
      -            "description": "Publication type (e.g., article, inproceedings)",
      -            "type": "string"
      -          },
      -          "url": {
      -            "description": "DBLP URL for the publication",
      -            "type": "string"
      -          },
      -          "venue": {
      -            "description": "Conference or journal name",
      -            "type": "string"
      -          },
      -          "year": {
      -            "description": "Publication year",
      -            "type": "number"
      -          }
      -        },
      -        "type": "object"
      -      },
      -      "type": "array"
      -    },
      -    "hits": {
      -      "description": "Total number of results matching the query",
      -      "type": "number"
      -    },
      -    "published": {
      -      "description": "Number of results in this response",
      -      "type": "number"
      -    },
      -    "start": {
      -      "description": "0-based offset of first result",
      -      "type": "number"
      -    }
      -  },
      -  "type": "object"
      -}
    • addedOutput schema / properties / source
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / total
      Added value: +{
      +  "description": "Total matches; null when not counted",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / total_note
      Added value: +{
      +  "description": "Present when the total is not counted",
      +  "type": "string"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / hits / description
      Previous value: -"Results per page, 1-1000 (default 30)"New value: +"Results per page, 1-100 (default 30)"
    • changedInput schema / properties / query / description
      Previous value: -"Search term — title / author / DOI / venue"New value: +"Title words, an author name, a venue or a year, e.g. \"attention is all you need\" or \"Yoshua Bengio\""
  3. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), but the description adds genuinely new behavioral facts: results come from a stored copy of the bulk release rather than a live index, matches are grouped and ordered newest-first within each class, phrase input is tried as a phrase first, and every response carries data_as_of, answered_from and licence. That freshness provenance is exactly the kind of 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.

Conciseness5/5

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

Three sentences, front-loaded with what the corpus is, then how matching works, then result ordering and envelope guarantees, closing with the count limits. No filler or repeated annotation content; every clause carries information an agent needs to form a query and interpret the response.

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?

An output schema exists, so return values needn't be spelled out, yet the description still flags the enclosing metadata fields. For a three-parameter read-only search this is nearly complete; the only gap is that it never states what a result record contains at a high level or clarifies its relationship to the author-search sibling.

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 real semantics beyond the schema: query matching covers title words, author, venue and year, and a quoted title or author is matched as a phrase first. This is matching behavior an agent would not learn from the schema's terse parameter text; hits/first only repeat defaults and caps.

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?

The description states a specific verb (search) plus the exact resource and corpus: the dblp CS bibliography with ~10M papers, articles, theses and proceedings, drawn from the publisher's CC0 bulk release. It also names the matchable fields (title, author, venue, year). It stops short of distinguishing itself from the sibling dblp_search_authors, which is the main remaining ambiguity.

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

Usage Guidelines3/5

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

Usage is implied rather than prescribed: it lists what the query can contain (title words, author name, venue, year) and gives example queries, which tells an agent how to phrase input. There is no explicit statement of when to prefer this over dblp_search_authors or search_venues, and no exclusions or prerequisites.

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.