Skip to main content
Glama

Opencitations

by io.github.pipeworx-io

Search Within a Source

search_within
Read-onlyIdempotent

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesThe document text to search inside (max ~200K chars).
limitNoMax passages to return (1-20, default 5).
queryYesNatural-language query — what passages do you want? E.g. "supply-chain risk", "fiscal year 2024 revenue", "drug interactions with warfarin".

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

While annotations already mark this as read-only/idempotent, the description adds substantial technical behavior: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, 200K char cap with truncation flagging, and output including character offsets and similarity scores. This is beyond what annotations convey.

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?

Five sentences, each carrying distinct value: purpose, usage, output details, pairing, and technical limitations. No redundancy; information is front-loaded with the core purpose first.

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?

The description covers purpose, use case, return values (top-N passages with offsets and similarity scores), technical mechanism, and limitations (200K cap). Since there is no output schema, it sufficiently explains what the agent can expect.

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% with descriptions for all parameters. The tool description adds useful examples for 'text' (e.g., SEC 10-K body, article) and clarifies the query's natural-language intent, but it doesn't significantly expand beyond the schema's parameter explanations.

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?

The description clearly states a specific verb+resource+scope: 'Semantic search INSIDE a fetched record.' It distinguishes from siblings by focusing on searching within an already-fetched document and explicitly pairs with ask_pipeworx_grounded, clarifying its complementary role.

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?

The description gives an explicit when-to-use: 'Use when the record is too big to cram into the prompt.' It also explains the value (saves context, returns only relevant passages) and mentions a paired tool, providing clear guidance on alternatives.

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

All Opencitations toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation2/5

Multiple tools have unclear boundaries: ask_pipeworx and ask_pipeworx_beta are described as currently identical, and citation vs citations differ only by pluralization while actually accepting different ID types (OCI vs DOI). The server is named Opencitations but 31 of 37 tools serve unrelated purposes, so an agent cannot infer what the set is for without reading very long descriptions.

Naming Consistency3/5

All names are snake_case and family prefixes (polymarket_*, ask_pipeworx_*, pipeworx_*) give some predictability. However, conventions are mixed: bare resource nouns (citation, citations, references, metadata) coexist with verb_noun tools (resolve_entity, validate_claim) and noun phrases (recent_changes, entity_profile, deep_research), so there is no single pattern that lets an agent predict tool names.

Tool Count2/5

37 tools is well past the 25+ threshold for a heavy set, and most are redundant with the server's own router tools — ask_pipeworx already reaches 5,759 underlying tools, making many direct tools overlapping conveniences. The scope also wildly overshoots the server name: only 6 of 37 tools serve the Opencitations citation-graph domain.

Completeness3/5

For the named OpenCitations domain, the core citation-graph read operations exist (metadata, incoming citations, outgoing references, counts, OCI record lookup), but there is no paper/DOI discovery or search tool — an agent must already possess a DOI, a dead end for title/author queries. The broader accidental domain (data routing, company research, prediction markets, monitoring) is covered unusually well, but that does not serve the server's stated purpose.

Resources