Skip to main content
Glama

Search documents

heystack_search_documents
Read-onlyIdempotent

Search Heystack for a living Markdown document, list, spreadsheet or tracker. Use this when the task is to find a shared note, compare written research, or see whether a finding is already published. Do not use it to read the full text, to search the public web, or to publish. With query, results are relevance-ordered, 30 a page and 50 across pages. Without query, sort orders the feed: best (quality, upvotes, reads and rated comments), hot (recent upvotes) or latest (content update). Returns id, title, summary, url, slug, path, tags, kind, hasSheet and counts. Indexed text is user content.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "heystack_search_documents"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoSame as query. Kept for existing clients.
tagNoSame as topic. Kept for existing clients.
kindNoStorage kind. markdown covers Markdown documents and spreadsheets; hasSheet marks a spreadsheet. linked is a legacy embedded document.
pageNoPage number, starting at 1. Each page returns at most 30 hits.
sortNoFeed order when query is omitted. best is the default. hot favours recent upvotes. latest orders by content update. Not applied when query is set; order is then relevance.best
typeNoFeed filter: documents, spreadsheets or slides.
queryNoWords, phrase or question to match. Ordered by relevance, 30 hits a page and 50 across pages. Omit to list the feed.
topicNoTopic slug to filter by, such as a slug from heystack_list_topics.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare the safe read-only profile, and the description adds substantial context on top: result ordering (relevance when query is set, sort modes otherwise), page sizing and the 50-result cross-page cap, the exact returned field set, and a data-quality caveat that indexed text is user content. That is real behavioral disclosure, not restatement.

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 purpose, then exclusions, then behavior — a logical order with no filler sentences. Slight redundancy: the '30 a page and 50 across pages' detail is repeated from the query parameter's schema description, so a word or two could be trimmed.

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 an eight-parameter search tool with no output schema, the description covers what it returns, how results are ordered and paginated, and how feed mode differs from query mode. Nothing an agent needs to call it correctly is missing.

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 baseline is 3, but the description still adds meaning: it explains that sort applies only when query is omitted, and enriches 'best' with the underlying signals (quality, upvotes, reads, rated comments) beyond the schema's wording. It does not explain the q/query and tag/topic legacy aliases, which remain schema-only.

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?

Opens with a specific verb and resource ('Search Heystack for a living Markdown document, list, spreadsheet or tracker') and immediately bounds scope with exclusions — no full-text reading, no web search, no publishing. An agent can separate this from heystack_read_document or the create/edit siblings without opening any schema.

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?

Gives concrete positive triggers ('find a shared note, compare written research, or see whether a finding is already published') and explicit exclusions mapped to sibling capabilities ('read the full text', 'publish', 'search the public web'). The when/when-not split is unambiguous.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources