Skip to main content
Glama
Sign In

Kaiku

by tech.kaiku.mcp
OverviewDiscussionsAdmin

Export sources bib

export_sources_bib
Read-only

A project's register of sources as a BibTeX file's text: one entry per source, its key the source's (what \cite{} and [@KEY] name), the identifiers as eprint/archivePrefix (arXiv), doi, mrnumber, zbl, isbn; a source with the † says so in a comment above its entry. 'keys' narrows it to those sources; 'page' to the ones a wiki page of the project cites ([@KEY], or [KEY] where the key is a source's), in the order it first cites them. A paper's build fetches the same file by token at /api/projects/{project}/sources.bib (?page= for a page's), with an ETag. Anybody who sees the project.

Input Schema

NameRequiredDescriptionDefault
keysNoOnly these sources: keys separated by commas, e.g. 'GS90,IMP26'.
pageNoOnly the sources this wiki page cites: its id.
projectYesThe project key, e.g. MATH.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / page
      Added value: +{
+  "default": null,
+  "description": "Only the sources this wiki page cites: its id.",
+  "type": [
+    "integer",
+    "null"
+  ]
+}
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

With annotations already covering read-only/non-destructive/closed-world, the description still adds substantial context: the exact entry format, identifier fields (eprint/archivePrefix, doi, mrnumber, zbl, isbn), the † comment marker, ordering behaviour for 'page', and the API/token/ETag equivalent. It also discloses the permission requirement ('Anybody who sees the project'), which is real behavioral information.

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?

The purpose is front-loaded and no sentence is filler, though the writing is compressed into long run-on clauses ('one entry per source, its key the source's...') that take a second read. Dense but every element earns its place.

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?

No output schema exists, and the description compensates by describing the returned file's structure, entry keys, identifier mapping, and comment markers. With permissions and filter behavior also stated, an agent has everything needed to call and interpret this tool.

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 100%, so the baseline is 3, but the description adds semantics beyond the schema: that 'page' restricts to sources cited by that wiki page and preserves first-citation order, and that 'keys' selects an explicit set. The key-format detail (\cite{} / [@KEY]) also clarifies what the filter values mean.

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: a project's register of sources rendered as a BibTeX file's text, plus exactly what each entry contains. An agent can tell this apart from import_sources_bib or list_sources without opening any schema.

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?

It explains how the two filters narrow the export ('keys' to specific sources, 'page' to sources a wiki page cites in first-citation order), which implies when to use each. But it never names a sibling alternative or states when not to use it (e.g. versus list_sources for plain metadata), so routing guidance is only implied.

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

All Kaiku toolsInspect
Try in Browser
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources