Skip to main content
Glama

search_literature

Read-only

Find papers and books by title or bibliographic query, returning ranked candidates with handles, authors, year, IDs, and open-access status for direct reading.

Instructions

Finds papers and books — by TITLE or bibliographic query: "find the paper about X", "is there a PDF of ". Call search_literature{query:"Attention Is All You Need", type:"paper"}. Returns a === [n/N] {title} block per ranked candidate — handle, type · authors · year, ids, open access; pass the handle unchanged to read in publications — then sources:, each one's status. "No candidate works found" with every source answered = nothing matched; a failed source is named, its records missing; an error result = every source failed, retry or read an exact identifier.

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_literature"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoany (default), paper, or book.
limitNoMaximum number of candidate works to return, default 8 and maximum 25.
queryYesA paper or book TITLE, or a free-text bibliographic query.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and idempotentHint=false; the description goes well beyond them by specifying the exact per-candidate block layout (`=== [n/N] {title}` with handle, type, authors, year, ids, open access), the trailing sources-and-status section, and the precise meaning of three distinct outcomes (empty result, partial source failure, total failure). This is unusually complete behavioral disclosure for a read-only search.

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?

Front-loaded with the purpose and an example call before the return-format detail, and nearly every clause carries new information (block layout, handle handoff, error semantics). It is dense to the point of being run-on in the return-format sentence, which slightly hurts scannability.

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?

There is no output schema, so the description carries the full burden of explaining results, and it does: candidate block structure, source status reporting, and the distinction between 'no matches', partial source failure, and total failure. Combined with the sibling handoff to `read`, an agent has everything needed to call it and interpret the response.

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 100%, so the schema already documents `query`, `type` (any/paper/book) and `limit` (default 8, max 25). The description adds only the worked example `search_literature{query:"Attention Is All You Need", type:"paper"}` and says nothing about `limit` or the allowed `type` values, so it sits at the baseline rather than exceeding it.

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 and resource ('Finds papers and books') and explicitly narrows the input mode to TITLE or bibliographic query. It is clearly distinguishable from siblings like `read` (which consumes the returned handle) and `download_file`, and even supplies a concrete example invocation.

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?

Gives natural-language trigger phrases ('find the paper about X', 'is there a PDF of <title>') and an explicit downstream handoff: pass the handle unchanged to `read` in publications. It also implies the alternative path when it says 'retry or read an exact identifier', though it never states plainly when to skip this tool in favor of going straight to an identifier.

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

Deploy Server

Other Tools