Skip to main content
Glama

Search Scholar

search_scholar
Read-onlyIdempotent

Searches Google Scholar and returns up to 20 publications (title, url, publication, snippet, cited_by, cites_id), optionally limited to a range of publication years. Use it for academic papers and citation counts. It does not return full texts, is not for patents (use search_patents) and is not general web search (use google_search). A search with no matches is charged; errors are not. Required: query.

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_scholar"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoZero-based results page, integer from 0: 0 is the first page, 1 the second, e.g. 1. Omit for the first page; each page is a separate charged call.
queryYesScholarly search text, 1-500 characters, e.g. "retrieval augmented generation"; author: and source: operators work.
resultsNoMaximum publications returned, integer 1-20, default 10, e.g. 5.
year_toNoLatest publication year included, four digits, e.g. 2026. Omit for no upper bound.
languageNoTwo-letter language code for the interface and results, e.g. "en" or "de". Omit for the source default, en.
year_fromNoEarliest publication year included, four digits, e.g. 2020. Must not be after year_to. Omit for no lower bound.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / language / description
      Previous value: -"Two-letter language code for scholarly results."New value: +"Two-letter language code for the interface and results, e.g. \"en\" or \"de\". Omit for the source default, en."
    • changedInput schema / properties / page / description
      Previous value: -"Zero-based scholarly result page number."New value: +"Zero-based results page, integer from 0: 0 is the first page, 1 the second, e.g. 1. Omit for the first page; each page is a separate charged call."
    • changedInput schema / properties / query / description
      Previous value: -"Scholarly search query."New value: +"Scholarly search text, 1-500 characters, e.g. \"retrieval augmented generation\"; author: and source: operators work."
    • changedInput schema / properties / results / description
      Previous value: -"Maximum number of scholarly results to return."New value: +"Maximum publications returned, integer 1-20, default 10, e.g. 5."
    • changedInput schema / properties / year_from / description
      Previous value: -"Earliest publication year to include."New value: +"Earliest publication year included, four digits, e.g. 2020. Must not be after year_to. Omit for no lower bound."
    • changedInput schema / properties / year_to / description
      Previous value: -"Latest publication year to include."New value: +"Latest publication year included, four digits, e.g. 2026. Omit for no upper bound."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Read-only and open-world are already in annotations, but the description adds genuinely new behavior: a 20-result cap, and a cost model ('a search with no matches is charged; errors are not'). That billing detail is exactly the kind of non-obvious trait an agent needs before calling, and nothing contradicts the annotations.

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?

Four dense sentences, front-loaded with what is returned, then usage, then exclusions, then billing and the required param. No filler and no repetition of schema text; every clause carries information.

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 no output schema, the description correctly enumerates return fields and adds limits, cost behavior, and sibling routing — enough to call correctly. The one gap is that it says nothing about pagination cost beyond the schema's own note, but the schema covers that, so the omission is minor.

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 coverage is 100%, so page, results, year_from/year_to, and language are already fully documented in the schema. The description only echoes the required param ('Required: query') and the year-range option, adding no syntax or format detail beyond what the schema provides. Baseline 3 applies.

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?

States a specific verb+resource (searches Google Scholar) and enumerates the exact return fields (title, url, publication, snippet, cited_by, cites_id). It also explicitly distinguishes itself from two named siblings (search_patents, google_search) and disclaims full-text retrieval, so an agent can identify 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.

Usage Guidelines5/5

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

Gives explicit positive guidance (academic papers and citation counts) and explicit exclusions with named alternatives: patents → search_patents, general web → google_search. The conditions that select each alternative are stated, not implied.

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