Skip to main content
Glama

Nypl

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".

TDQS

A5/5.0
Behavior5/5

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds substantive behavior: BGE-base-en embeddings, cosine similarity on 500-char overlapping windows, 200K-char cap with truncation and flagging, and the return format (passages with offsets + scores). No contradiction with annotations.

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?

Three sentences, front-loaded with the core function, then usage, then technical cap. Each sentence carries unique information with no filler, making it efficient and well-structured.

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, but the description compensates by specifying the return format (top-N passages with character offsets and similarity scores). It also covers limits, pairing with a sibling tool, and technical details, making the tool fully self-explanatory.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description enriches both 'text' (e.g., SEC 10-K body, article, long tool result) and 'query' (e.g., 'supply-chain risk', 'drug interactions with warfarin'), making parameter semantics more concrete and actionable than the schema alone.

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 opens with 'Semantic search INSIDE a fetched record,' clearly identifying the verb (search) and resource (a fetched record). It differentiates from sibling tools by emphasizing it operates on already-pulled text rather than external sources, and specifies the return of top-N passages with character offsets.

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?

Explicitly states 'Use when the record is too big to cram into the prompt' and explains the benefit (saves context, returns only relevant passages). It also pairs with ask_pipeworx_grounded, giving the agent a clear workflow: fetch, search within, then ground over passages.

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

All Nypl 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
Disambiguation4/5

Most tools have distinct purposes, with clear descriptions differentiating similar ones like ask_pipeworx and ask_pipeworx_grounded. A few overlaps exist (multiple Polymarket analysis tools), but descriptions sufficiently resolve ambiguity.

Naming Consistency2/5

Tool naming is inconsistent, mixing descriptive phrases (entity_profile, polymarket_edges) with verb-object patterns (generate_llms_txt, search). No strong convention is followed, and the 'polymarket_' prefix is applied to some betting tools but not others.

Tool Count3/5

32 tools is high but not extreme. However, the scope is too broad for a single server, covering data queries, betting, memory, NYPL, and more, making the set feel bloated and unfocused.

Completeness2/5

The domain is unclear due to mixed tools, but within the NYPL subset there are clear gaps (only search and item, no CRUD). For the other domains, coverage is uneven and lacks clear lifecycle completeness.

Resources