Skip to main content
Glama

Htmltext

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

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. Description adds rich behavioral detail: uses BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, 200K char cap with truncation flag, and each passage includes character offsets for verification. Goes well beyond annotations.

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

Conciseness4/5

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

Front-loaded with key purpose, then use case, then pairing, then technical details. Efficient but could be more scannable with breaks. Every sentence adds value, no redundancy.

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?

Covers input, output (top-N passages with offsets and scores), use case, pairing, algorithm, window size, char cap, and truncation behavior. No output schema, but description adequately explains return values. Complete for a retrieval tool of moderate 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 detailed descriptions (max chars for text, 1-20 range for limit, NL examples for query). Description adds little beyond schema: it provides context on how query works (natural-language) and mentions limit default, but these are already in schema. Baseline 3 is appropriate.

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?

Clearly states it performs semantic search inside a fetched record, with specific examples (SEC 10-K, article, tool result). Distinguishes from sibling tools by mentioning pairing with ask_pipeworx_grounded and contrasting with whole-document retrieval.

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?

Explicitly says when to use: when the record is too large to fit in the prompt, saving context. Suggests pairing with ask_pipeworx_grounded, but does not explicitly state when not to use or list alternatives beyond that pair.

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

All Htmltext 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

Several tools have overlapping or nested roles: ask_pipeworx_beta is explicitly identical to ask_pipeworx currently, ask_pipeworx_grounded uses the same router, and polymarket_arbitrage/polymarket_edges both surface mispricings. ai_visibility_check and scan_competitor_ai_presence are also tightly coupled, making tool selection error-prone.

Naming Consistency3/5

Names are uniformly snake_case and mostly readable, but the pattern is mixed: verb-first names like extract_links and discover_tools coexist with noun-first product names like polymarket_edges and entity_profile, plus bare verbs like remember and forget. This breaks the predictable verb_noun convention.

Tool Count2/5

34 tools is far too many for a server named Htmltext, and most tools are unrelated to HTML processing. Even as a broad data-research server, the count exceeds the usual 3-15 sweet spot and includes meta-tools, near-duplicate query modes, and niche utilities that bloat the surface.

Completeness3/5

The set is unusually broad—covering data research, prediction markets, memory, subscriptions, HTML extraction, AI visibility, and package scanning—but no single domain is fully fleshed out. HTML tools only do extraction, prediction-market tools lack a simple market browser, and there is no general web fetch tool. Most gaps can be worked around via ask_pipeworx, but the surface feels like a grab bag rather than a cohesive lifecycle.

Resources