Skip to main content
Glama

Mesh

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. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. The description adds significant behavioral context: embedding model (BGE-base-en), chunking strategy (500-char overlapping windows), similarity metric (cosine), character limit (200K chars with truncation flag). This goes well beyond annotations and is fully consistent.

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?

The description is three sentences, each serving a distinct purpose: purpose, usage guidelines, and technical details. It is front-loaded and contains no redundant or unnecessary words.

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?

Despite no output schema, the description fully explains the return value (passages with character offsets and similarity scores), covers technical constraints (max 200K chars, truncation flag), and integrates well with sibling tools. It is complete for the tool's complexity.

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% with descriptions for all 3 parameters. The description adds minimal extra semantics: it clarifies that 'text' is the fetched record and encourages natural-language examples for 'query'. This is baseline 3 as per guidelines.

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 uses a specific verb ('semantic search') and resource ('inside a fetched record'), providing concrete examples like SEC 10-K body and long tool results. It also distinguishes itself from siblings by mentioning its pairing with ask_pipeworx_grounded.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use ('record too big to cram into the prompt') and explains the benefit (saves context, returns relevant passages with offsets). It also suggests a complementary tool (ask_pipeworx_grounded). While it doesn't explicitly say when not to use, the guidance is clear and sufficient.

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

All Mesh 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

A4/5.0
Disambiguation3/5

The three ask_pipeworx variants are a genuine confusion risk — ask_pipeworx_beta is currently described as identical to ask_pipeworx, and ask_pipeworx_grounded differs only in extraction strictness. search_descriptors and resolve_term also overlap heavily (both map a term to MeSH descriptor IDs). The six Polymarket tools are differentiated by rich descriptions but still form a dense cluster where misselection is plausible.

Naming Consistency4/5

Most tools follow a clean verb_qualifier pattern (ask_, bet_, compare_, resolve_, search_, validate_) with the brand as a namespace (ask_pipeworx, pipeworx_trending, polymarket_*). Minor deviations exist: pipeworx_feedback and pipeworx_trending lead with a noun, the memory trio (remember, recall, forget) are bare verbs, and the ask_pipeworx family uses a brand name rather than a resource noun — but the overall pattern stays predictable and readable.

Tool Count2/5

At 34 tools this exceeds the threshold where a set feels heavy, and the bloat is visible: three near-identical ask_pipeworx routers and a six-tool Polymarket suite dominate. Several tools (generate_llms_txt, scan_dependency, bet_research) feel like accreted one-offs rather than part of a coherent surface. The broad platform purpose justifies some breadth, but the count is inflated by redundant variants.

Completeness4/5

The core purpose — universal access to authoritative structured data — is well covered via the router, grounded mode, deep_research, entity/profile/compare/validate wrappers, and discovery tools. The subscription lifecycle (subscribe/unsubscribe/list/alerts) and memory (remember/recall/forget) have no dead ends. Minor gaps exist: non-polymarket prediction-market workflows lack the depth of the Polymarket cluster, and the single-purpose niche tools fit awkwardly, but agents won't hit dead ends.

Resources