Skip to main content
Glama

Search publications

search_publications
Read-onlyIdempotent

AND-filtered bibliography, newest first. Keyword includes PDF text and returns match snippets. citation_format returns citations per page; export links every match as one file. Cite amira_url.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_publications"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoExact type; discover values with list_publication_facets
limitNoDefault 25; max 100 summaries or 25 citation_format rows, also byte-bounded. export ignores it
venueNoJournal/book title, partial
authorNoAuthor/editor name, either name order
exportNoReturn a file link instead of rows
offsetNo
keywordNoTitle, abstracts, venue, subjects or full text; every word must match, quote a phrase
subjectNoSubject heading, partial
year_toNo
languageNoLanguage name or ISO code
year_fromNo
added_sinceNoAdded to AMIRA on or after this ISO date
has_fulltextNoFilter by extracted full-text availability
citation_formatNoOmit for summaries; pages carry bibtex, ris or csl_json

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Default 25; max 100 summaries or 25 exports, also byte-bounded"New value: +"Default 25; max 100 summaries or 25 citation_format rows, also byte-bounded. export ignores it"
  2. Changed1 schema field changed
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
  3. Changed1 schema field changed
    • removedInput schema / properties / limit / maximum
      Removed value: -9007199254740991
  4. Changed10 schema fields changed
    • addedInput schema / properties / added_since
      Added value: +{
      +  "description": "Added to AMIRA on or after this ISO date",
      +  "maxLength": 40,
      +  "type": "string"
      +}
    • addedInput schema / properties / author / maxLength
      Added value: +1000
    • changedInput schema / properties / citation_format / description
      Previous value: -"Omit for summaries; export results contain bibtex, ris or csl_json"New value: +"Omit for summaries; pages carry bibtex, ris or csl_json"
    • addedInput schema / properties / export
      Added value: +{
      +  "description": "Return a file link instead of rows",
      +  "enum": [
      +    "csv",
      +    "jsonl",
      +    "bibtex",
      +    "ris",
      +    "csl-json"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / keyword / description
      Previous value: -"Title, abstract, venue, subjects or full text; substring match"New value: +"Title, abstracts, venue, subjects or full text; every word must match, quote a phrase"
    • addedInput schema / properties / keyword / maxLength
      Added value: +1000
    • addedInput schema / properties / language / maxLength
      Added value: +1000
    • addedInput schema / properties / subject / maxLength
      Added value: +1000
    • addedInput schema / properties / type / maxLength
      Added value: +1000
    • addedInput schema / properties / venue / maxLength
      Added value: +1000
  5. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered; the description adds genuinely new behavior: AND filter semantics, newest-first ordering, keyword extending to PDF text with match snippets, citation_format producing per-page citations, and export collapsing every match into one file link. It omits edge behavior such as empty-result handling or result shape, which keeps it off a 5.

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?

Four compact sentences with the core retrieval semantics front-loaded and no filler; every clause carries information. It is slightly cryptic in places — "AND-filtered" and the bare instruction "Cite amira_url" are compressed to the point of needing interpretation.

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

Completeness3/5

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

For a 14-parameter tool with no output schema, the description covers the highest-risk behaviors (full-text keyword scope, limit interactions, export vs. citation_format) but says nothing about traversing results by offset, how ordering interacts with paging, or what a returned summary/row contains. Adequate but with real gaps given the tool's complexity.

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 high (79%) and the schema already documents individual filters, so the baseline is 3. The description adds cross-parameter meaning the schema cannot convey: that keyword reaches into PDF text and returns snippets, and that citation_format splits results per page while export returns a single file link covering every match.

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 names the resource ("bibliography") and its core semantics: AND-combined filters, sorted newest first. It is clear what the tool retrieves and how, but never uses a search verb explicitly and does not distinguish itself from sibling search tools such as search or get_publication, so an agent must infer the boundary from the name alone.

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 guidance is implied through mode selection (keyword for full-text matching, citation_format vs. export for output shape), which helps an agent pick parameters. However there is no explicit when-to-use or when-not-to-use guidance relative to the many sibling search and get_publication tools, so the alternatives decision is left to inference.

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.