Skip to main content
Glama

Search papers

search_papers
Read-onlyIdempotent

Use this to find the papers themselves: when the user asks which studies exist or what papers say on a subject in the biology of aging or an age-related disease, often without the word aging: senolytics, epigenetic clocks, partial reprogramming, mitochondria, NAD+, immune aging, ovarian aging and menopause, neurodegeneration, sarcopenia, long-lived species. Pass 2 to 4 key terms, not the question: "rapamycin lifespan mice", not "does rapamycin extend lifespan in mice". Searches the titles and abstracts of every paper AgingResearch.News has read, best match first, by default only papers about aging. Supports "quoted phrases", OR, -exclusions and the filters below. When the terms together find fewer than 3 papers, a misspelling is corrected and the commonest terms set aside (relaxed: true). The record is not all of PubMed: no match does not mean no study exists. Not for personal medical advice, symptoms or product recommendations. Read one in full with get_paper.

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": {
      "q": "<q>"
    },
    "name": "search_papers"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesSearch terms: 2 to 4 key terms work best. Supports "quoted phrases", OR and -exclusions.
limitNoResults per page.
sinceNoOnly papers added on or after this date (YYYY-MM-DD).
untilNoOnly papers added on or before this UTC date (YYYY-MM-DD).
authorNoPapers by an author. A name matches every author who answers to it: the words in any order, with or without accents, an initial standing for any name it begins (`sinclair d`). An `author_id` from a paper's `authors_full` (an OpenAlex author id such as `A5022713595`, or an ORCID iD) matches that one person.
cursorNoFrom the last page's `pagination.next_cursor`; keep the other arguments the same.
systemNoBody system key (see `systems`). A paper matches when it involves any of them. Only papers that have been analyzed have systems.
age_linkNoHow the work itself connects to aging.
categoryNoCategory slug. A paper matches when its category or its secondary category is listed.
preprintNo`true` for preprints only, `false` for peer-reviewed papers only. Omit for both.
study_typeNoMain source of evidence.
min_relevanceNoHow closely papers must bear on aging, 0 to 3. Leave out for papers about aging; 1 adds adjacent papers; 0 returns every paper read, most of them not about aging.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / since / description
      Previous value: -"Only papers added on or after this UTC date (YYYY-MM-DD; a full ISO timestamp is cut to its date)."New value: +"Only papers added on or after this date (YYYY-MM-DD)."
  2. Changed7 schema fields changed
    • removedInput schema / properties / age_link / examples
      Removed value: -[
      -  [
      -    "lifespan_healthspan",
      -    "aging_lever"
      -  ]
      -]
    • removedInput schema / properties / category / examples
      Removed value: -[
      -  [
      -    "interventions"
      -  ]
      -]
    • changedInput schema / properties / cursor / description
      Previous value: -"Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same."New value: +"From the last page's `pagination.next_cursor`; keep the other arguments the same."
    • changedInput schema / properties / limit / description
      Previous value: -"Results per page, 1 to 25."New value: +"Results per page."
    • changedInput schema / properties / q / description
      Previous value: -"Search terms. Supports \"quoted phrases\", OR and -exclusions."New value: +"Search terms: 2 to 4 key terms work best. Supports \"quoted phrases\", OR and -exclusions."
    • removedInput schema / properties / study_type / examples
      Removed value: -[
      -  [
      -    "human_trial",
      -    "animal"
      -  ]
      -]
    • removedInput schema / properties / system / examples
      Removed value: -[
      -  [
      -    "brain-nerves",
      -    "muscle"
      -  ]
      -]
  3. Changed1 schema field changed
    • changedInput schema / properties / system / description
      Previous value: -"Body system key (see `systems`). A paper matches when it involves any of them."New value: +"Body system key (see `systems`). A paper matches when it involves any of them. Only papers that have been analyzed have systems."
  4. Changed5 schema fields changed
    • changedInput schema / properties / age_link / description
      Previous value: -"How the work itself connects to aging (see `judgement.age_link`)."New value: +"How the work itself connects to aging."
    • changedInput schema / properties / min_relevance / description
      Previous value: -"Lowest aging-relevance score to include (0 to 3, see `judgement.relevance`). Without it, the papers the site shows; 1 adds tangential papers; 0 returns every paper ARN read, most of which are not about aging."New value: +"How closely papers must bear on aging, 0 to 3. Leave out for papers about aging; 1 adds adjacent papers; 0 returns every paper read, most of them not about aging."
    • changedInput schema / properties / since / description
      Previous value: -"Only papers that entered ARN on or after this UTC date (YYYY-MM-DD; a full ISO timestamp is cut to its date)."New value: +"Only papers added on or after this UTC date (YYYY-MM-DD; a full ISO timestamp is cut to its date)."
    • changedInput schema / properties / system / description
      Previous value: -"Body system key (see `systems`). A paper matches when it involves any of them. Only papers that have been through extraction have systems."New value: +"Body system key (see `systems`). A paper matches when it involves any of them."
    • changedInput schema / properties / until / description
      Previous value: -"Only papers that entered ARN on or before this UTC date (YYYY-MM-DD)."New value: +"Only papers added on or before this UTC date (YYYY-MM-DD)."
  5. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations it discloses ranking ('best match first'), the implicit default aging filter, the automatic relaxation behavior with the relaxed:true flag when fewer than 3 hits, and the corpus coverage caveat ('no match does not mean no study exists'). That last point is exactly the kind of behavioral disclosure an agent needs and no annotation supplies.

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 purpose, then query syntax, then fallback behavior, then a scope caveat — a sensible order with no filler sentences. The topical keyword list is long but earns its place by teaching query vocabulary; a tighter phrasing would still preserve the value.

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?

For a 12-parameter search tool with no output schema, the description covers what is searched, how results are ordered, what the default scope is, what happens on thin results, and how to continue to full text — the important operational facts. Pagination and facet details are left to a fully described schema, which is a reasonable division of labor.

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 the baseline applies, and the description's query advice ('2 to 4 key terms, not the question') meaningfully restates and reinforces the `q` semantics with a good counter-example. However, the 11 filter/pagination parameters are waved at only as 'the filters below' — a dangling reference with no explanation of system, age_link, min_relevance, or cursor use.

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?

Specific verb+resource ('find the papers themselves') with the scope and corpus named (titles and abstracts of every paper AgingResearch.News has read). It explicitly contrasts with get_paper ('Read one in full with get_paper') and with personal medical/product queries, so an agent can distinguish it from siblings without opening a 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 the trigger condition (user asks which studies exist or what papers say on a topic, 'often without the word aging'), supplies concrete example topics to map colloquial queries, and states exclusions ('Not for personal medical advice, symptoms or product recommendations') plus the handoff for full text.

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.