Skip to main content
Glama

Carbon Interface

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

A4.9/5.0
Behavior5/5

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

Despite readOnlyHint=true and destructiveHint=false, the description adds critical behavioral detail: text is split into 500-char overlapping windows, uses BGE-base-en embeddings and cosine similarity, has a 200K char cap with truncation flagged, and every passage includes offsets. This goes well beyond annotations and discloses potential edge cases (truncation) and retrieval mechanics.

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 well-structured with a clear opening sentence, usage context, technical details, and a pairing note. All sentences earn their place, no fluff. It's moderately sized but information-dense, front-loaded with purpose and then specifics.

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?

For a tool with no output schema, the description thoroughly explains what the agent receives (passages with offsets and similarity scores), the algorithm, limits, and truncation behavior. It covers the full scope: purpose, use case, mechanics, edge cases, and integration with siblings. Given the tool's moderate complexity, it is complete.

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 schema already describes all three params. The description adds value by explaining the query parameter with concrete examples and clarifying the 'text' param as the fetched record content. However, it doesn't add much detail about 'limit' beyond the schema, but the examples and cap context are helpful. Baseline 3, plus extra value from examples and integration context.

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 it performs semantic search inside a fetched record (e.g., SEC filing, article) using a natural-language query, returning top-N passages with offsets and scores. It explicitly distinguishes itself from siblings by pairing with ask_pipeworx_grounded and emphasizing its in-place search role, making it unique among tools like ask_pipeworx or deep_research.

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 explicit use cases: when the record is too big to fit in the prompt, to save context, and to verify quotes via offsets. It also mentions pairing with ask_pipeworx_grounded, providing a clear alternative workflow. It does not explicitly say when not to use it, but the context is strong enough.

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

All Carbon Interface 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

A3.8/5.0
Disambiguation2/5

Multiple tools are near-duplicates or heavily overlap: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are nearly identical, several polymarket_* tools cover the same edge-detection domain, and scan_competitor_ai_presence is just a wrapper around ai_visibility_check. Agents will frequently struggle to pick the right tool.

Naming Consistency3/5

Most tools use snake_case, but the pattern is inconsistent: verb_noun (estimate_electricity, resolve_entity), noun_phrase (entity_profile, recent_changes), brand-specific (ask_pipeworx, pipeworx_trending), and family-prefixed (polymarket_*). The naming is readable but lacks a single cohesive convention.

Tool Count2/5

At 34 tools, the set is far larger than the 'Carbon Interface' name implies. It piles together carbon estimation, a massive data-router, prediction-market analysis, memory, subscriptions, and meta-tools, making the surface feel bloated and unfocused.

Completeness3/5

The carbon-estimation purpose is thin (only three estimators with no lifecycle), but the broader Pipeworx/data and prediction-market subdomains are fairly well covered. Gaps exist in each subdomain (e.g., no order placement for betting, no carbon scope beyond the three estimates), and the lack of a clear primary domain makes coverage hard to assess.

Resources