Skip to main content
Glama

iconify

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

A4.7/5.0
Behavior5/5

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

Annotations already mark this as readOnly/idempotent, but the description adds significant behavior: returns character offsets and similarity scores, uses BGE-base-en embeddings with cosine over 500-char overlapping windows, enforces a 200K char cap with truncation flag. This goes well beyond the annotations and provides concrete operational details.

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, each earning its place: core function, use case, and technical detail. It is front-loaded and well-structured with no redundancy or filler. The description is appropriately sized for the information it conveys.

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 return format (passages with offsets and similarity scores), input size cap, truncation behavior, and pairing with a sibling tool. It covers both the 'what' and the 'how' faithfully, making the tool self-contained for an agent.

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 parameter descriptions, so the baseline is 3. The description reinforces the text param by saying 'pass the text you already pulled' and implies limit via 'top-N,' but it doesn't add meaning beyond what the schema already provides. This is consistent with the high-coverage baseline.

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' — a specific verb+resource that clearly distinguishes it from sibling tools. It further specifies inputs (text + query) and outputs (top-N passages with offsets/scores), leaving no ambiguity about what the tool does.

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 the trigger: 'Use when the record is too big to cram into the prompt.' It also names a sibling pairing: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages.' This gives clear when-to-use and an alternative workflow, making it easy for an agent to select this tool appropriately.

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

All iconify 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

A3.6/5.0
Disambiguation1/5

Multiple tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route questions to the same data sources, and the Polymarket family (polymarket_edges, polymarket_edge_tracker, polymarket_arbitrage, polymarket_fill_risk, polymarket_kalshi_spread) has blurred boundaries. Agents would struggle to pick the right one without reading every description carefully.

Naming Consistency2/5

Naming is mostly snake_case but follows no consistent verb_noun pattern. Verbs vary widely (ask_, get_, list_, search_, compare_, scan_, validate_, remember, recall, forget, subscribe, unsubscribe, discover, generate, resolve, suggest) and many tools are bare nouns (entity_profile, recent_alerts, polymarket_edges). The inconsistency makes the set feel ad hoc.

Tool Count2/5

34 tools is on the heavy side, and the count is inflated by many near-duplicate data-router and prediction-market tools. The server is named 'iconify' yet only 3 of 34 tools actually relate to icons, indicating poor scoping for the stated purpose.

Completeness2/5

For the icon domain, the surface is minimal (list, search, get) with no create/update/delete. For the broader data/prediction-market domain, there are significant gaps in lifecycle coverage (e.g., subscriptions have create/cancel but no pause/resume, and the memory tools lack namespacing). The mixed focus means no single domain is fully covered.

Resources