Skip to main content
Glama

Clinicaltrials

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

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, etc. Description adds numerous behavioral details: character offsets, similarity scores, BGE-base-en embeddings, cosine, 500-char overlapping windows, 200K char cap with truncation flag. No contradiction.

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?

Concise: 4 sentences, front-loaded with action, efficient use of examples and technical details. No wasted 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?

Given 3 parameters, no output schema, rich annotations, and moderate tool complexity, the description covers behavior, constraints, usage context, and pairing with sibling. Fully complete.

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 covers 100% of parameters. Description adds meaningful context: 'max ~200K chars' for text, '1-20, default 5' for limit, and natural-language query examples. Adds value beyond schema.

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?

Description clearly states the verb 'semantic search' and resource 'a fetched record' with concrete examples (SEC 10-K, article). It distinguishes from siblings by mentioning pairing with ask_pipeworx_grounded and emphasizing contextual-saving value.

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 big to cram into the prompt'. No explicit 'when not to use' but the context is clear. Pairs with sibling tool for grounding.

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

All Clinicaltrials 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

A3.9/5.0
Disambiguation3/5

Tool families overlap in purpose—ask_pipeworx/ask_pipeworx_beta/ask_pipeworx_grounded, ct_search/ct_count_by_condition/ct_competitive_landscape, and ct_sponsor_trials/ct_sponsor_pipeline/ct_sponsor_activity all present multiple plausible entry points. The very detailed, cross-referenced descriptions help, but an agent still has to read carefully to avoid misselection.

Naming Consistency4/5

Nearly all tool names follow lowercase snake_case with recognizable prefixes like ct_, polymarket_, and pipeworx_, giving the set a strong overall pattern. The main deviation is noun-phrase names such as recent_changes, entity_profile, and pipeworx_trending instead of a more uniform verb-first convention.

Tool Count2/5

44 tools is far too many for a server named Clinicaltrials: only 13 are ct_* tools, while the other 31 are broad Pipeworx utilities covering prediction markets, memory, subscriptions, npm scanning, and AI visibility. The clinical-trial module itself is well-sized, but the server bundles substantial unrelated surface area.

Completeness4/5

The clinical-trial workflow is nearly complete: search, study details, results, counts, sponsor comparison and pipeline, location lookup, update tracking, and landscape mapping are all covered. Minor conveniences like saved searches or export are missing, but agents can work around them; there are no dead ends in the registry domain.

Resources