Skip to main content
Glama

Honeydew AI Documentation

by ai.honeydew

query_docs_filesystem_honeydew_documentation

Read-onlyIdempotent

Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at / that contains ONLY the Honeydew Documentation documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks.

This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its .mdx path (e.g. /quickstart.mdx, /api-reference/create-customer.mdx) to head or cat. To search the docs with exact keyword or regex matches, use rg. To understand the docs structure, use tree or ls.

Workflow: Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path.

Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run --help on any command for usage.

Each call is STATELESS: the working directory always resets to / and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with && or pass absolute paths (e.g., cd /api-reference && ls or ls /api-reference). Do NOT assume that cd in one call affects the next call.

Examples:

  • tree / -L 2 — see the top-level directory layout

  • rg -il "rate limit" / — find all files mentioning "rate limit"

  • rg -C 3 "apiKey" /api-reference/ — show matches with 3 lines of context around each hit

  • head -80 /quickstart.mdx — read the top 80 lines of a specific page

  • head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx — read multiple pages in one call

  • cat /api-reference/create-customer.mdx — read a full page when you need everything

  • cat /openapi/spec.json | jq '.paths | keys' — list OpenAPI endpoints

Output is truncated to 30KB per call. Prefer targeted rg -C or head -N over broad cat on large files. To read only the relevant sections of a large file, use rg -C 3 "pattern" /path/file.mdx. Batch multiple file reads into a single head or cat call whenever possible.

When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the .mdx extension. For example, /quickstart.mdx becomes /quickstart and /api-reference/overview.mdx becomes /api-reference/overview.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandYesA shell command to run against the virtualized documentation filesystem (e.g., `rg -il "keyword" /`, `tree / -L 2`, `head -80 /path/file.mdx`).

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already indicate read-only and no destruction, but the description goes further by explaining the sandbox nature, lack of network/process control, and statelessness. It clearly states this is not a real machine shell, fully aligning with 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?

The description is well-structured with paragraphs and bullet examples, but it is somewhat repetitive—several sentences restate the same sandbox and read-only guarantees. It could be tightened without losing key information.

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 the presence of sibling tools, the description fully explains when to use this one, covers output truncation and path-to-URL conversion, and provides enough detail for effective usage. No output schema exists, but the description addresses expected behavior sufficiently.

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?

The single parameter 'command' is fully described in the schema with examples, and the tool description adds comprehensive usage examples (e.g., 'rg -il', 'tree', 'head') that illustrate valid commands without ambiguity.

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 the tool runs read-only shell-like queries against a virtualized documentation filesystem. It distinguishes itself from sibling tools by focusing on shell command execution for structural exploration and exact content reading, not semantic search.

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 explicitly says when to use this tool versus the search tool, providing a workflow: 'Start with the search tool for broad or conceptual queries... Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path.'

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

All Honeydew AI Documentation 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

A4.2/5.0
Disambiguation4/5

The two main tools are clearly distinct: one performs filesystem-style queries on a virtual documentation tree, and the other is a semantic search over the knowledge base. The third tool, feedback submission, is entirely different in purpose. The only minor ambiguity is that the search tool and filesystem tool both retrieve documentation, but their descriptions clarify different use cases.

Naming Consistency3/5

Tool names are descriptive but not uniformly patterned. 'query_docs_filesystem_honeydew_documentation' uses verb-object with a suffix, 'search_honeydew_documentation' uses verb-noun, and 'submit_feedback' is a simple verb-noun. The inconsistency lies in the inclusion of the server name in some but not all, and the length of the first name is cumbersome, but the verbs are clear.

Tool Count4/5

Three tools is on the lean side but appropriate for a documentation assistant: one for structured file-system access, one for semantic search, and one for feedback. It avoids unnecessary redundancy and covers the core need. Slightly more could be added (e.g., a dedicated get_page tool), but the count is reasonable.

Completeness4/5

The tool set covers the essential workflows: searching for information, reading specific pages, and reporting issues. The filesystem tool can simulate file browsing and reading, which compensates for the lack of a dedicated 'get page' tool. A minor gap is the absence of a tool to list all pages or navigate with more advanced filters, but agents can work around this with tree/ls and rg.

Resources