Skip to main content
Glama
Sign In

Keystone

by io.github.Srikarmk
OverviewDiscussionsAdmin

Search what Keystone read

search_library

Search 2497 readings taken from 234 arXiv papers' LaTeX source: citation stances (adopts, extends, disputes, measures against) and stated assumptions. Matches on the quoted sentence, the cue phrase that decided it, and the work cited. Returns the sentence verbatim with a link to the exact line.

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_library"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoDefault 15.
queryYesText to look for, e.g. 'layer normalization'
stanceNoOptional filter. The first five are citation stances; bare/cited/shown are what an assumption's own sentence offers for it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses corpus size (2497 readings / 234 papers), what fields are matched, and the return shape ('sentence verbatim with a link to the exact line'). It stops short of stating result ordering, truncation behavior beyond the schema's limit cap, or that this is a read-only operation.

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

Conciseness5/5

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

Two dense sentences, front-loaded with scope and corpus, then matching behavior, then return format. No filler and nothing that repeats the schema verbatim.

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?

No output schema exists, and the description compensates by describing the returned sentence and line link. Corpus scale, match targets, and stance/assumption coverage make it callable, with only minor gaps (result ordering, stance vocabulary mismatch) left open.

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 is 3, and the description does add real value by saying the query matches quoted sentence, cue phrase, and cited work (broader than the schema's 'Text to look for'). However, it labels the stances 'adopts, extends, disputes, measures against' while the enum uses 'inherits, extends, contests, compares, background...', so an agent reading the prose could pass an invalid stance value.

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 concrete verb and resource ('Search 2497 readings... citation stances and stated assumptions') with explicit corpus scope (234 arXiv papers' LaTeX source). This clearly separates it from list_disagreements and read_paper in practice, though it never names those siblings to rule them out explicitly.

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 is only implied: the mention of matching on quoted sentence, cue phrase, and cited work suggests it is the tool for locating citation/assumption sentences. There is no explicit when-to-use, when-not-to-use, or pointer to the sibling tools for browsing or listing disagreements.

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

All Keystone toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources