Skip to main content
Glama

List sources

list_sources
Read-only

A project's sources — the papers, books and preprints its pages cite — each with its key (what a page cites it by, e.g. 'IMP26', a BibTeX key), its authors (the name as the work prints it, and 'personId'/'person' where it is a person of the project's register — 'hidden' where you may not see that person), title, year, venue (journal or publisher), identifiers ('arxiv' with its version, 'doi', 'mr', 'zbmath', 'isbn'), its PDF ('pdf': an attachment of an issue or a page, with its address — or 'hidden') and how far it is checked. 'check' is 'unchecked' (nobody checked it), 'api' (a service — arXiv, Crossref, zbMATH Open — agreed with it), 'mismatch' (it disagrees with what it names; 'checkNote' says how) or 'manual' (a person checked it against the original; 'checkedBy'). 'dagger' is true for unchecked and mismatch: the † a bibliography marks such a reference with. For an 'api' check, 'services.compared' says what each service was asked by and compared on — 'service', 'id' with its record's 'url', the arXiv 'version', 'fields' (authors, title, year: only those actually compared) and 'said', the line to quote: «Checked against Crossref by DOI …: authors, title and year agreed» — and 'notes', what agreed only with a note: 'garbled' (the service's encoding broken in those fields), 'year' (its year a year off the record's, which 'by' gives — another service, or its own 'print' or 'online' date), 'preprint' (arXiv's title differs from the published work's, which agrees). 'services.queued' is true while it waits for the background check, and 'queued' counts those for the whole project. Read a work's description here rather than from a page's own list. Ordered by key. Anybody who sees the project.

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": {
      "project": "<project>"
    },
    "name": "list_sources"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoWords its key, title, venue, an author's name or an identifier holds, case aside.
checkNoOnly sources so checked: unchecked, api, mismatch, manual — or 'dagger' for unchecked and mismatch together.
projectYesThe project key, e.g. MATH.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description still adds real context beyond that: the list is project-scoped and ordered by key, and visibility is limited to people who can see the project ('hidden' fields for restricted persons). It could have said more about pagination or size.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

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

The single run-on sentence packs in dozens of field definitions, quotes and examples, making it hard to scan and violating front-loading of the most important facts. Much of the detail describes return values, which belongs in an output schema rather than a prose block of this length.

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?

There is no output schema, and the description compensates thoroughly by documenting the meaning of every returned field, the check states, the dagger convention and the services/queued structure. Only minor gaps remain, such as result size and ordering stability.

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 q, check and project are already documented in the schema. The description restates the check vocabulary and explains the 'dagger' shorthand, but adds no search syntax or filtering semantics beyond what the schema supplies, so the baseline 3 applies.

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?

States a specific verb and resource ('A project's sources — the papers, books and preprints its pages cite') and enumerates the fields returned, so an agent knows exactly what it gets. It does not, however, distinguish itself from near siblings such as get_source, read_page_literature or export_sources_bib.

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?

The line 'Read a work's description here rather than from a page's own list' gives one explicit routing rule, and 'Anybody who sees the project' hints at the access condition. There is no guidance on when to use get_source (single source) or search_pdf_texts instead, so usage is only partially 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