Skip to main content
Glama
Sign In

Docsy

by io.github.getremcp
OverviewDiscussionsAdmin

Query Documentation

query-docs
Read-onlyIdempotent

Search one resolved library and exact version for source-linked documentation. Use response: links for publisher URLs without page bodies, or snippets for excerpts. Snippets default to 6,000 characters to keep agent context concise; set maxCharacters up to 50,000 for more. For unscoped discovery use search. Limit to 3 focused queries per question.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum results to return (snippets or links); omit to use the production default.
queryYesSpecific documentation concept to retrieve. Use one topic per query and never include secrets, credentials, PII, proprietary code, or confidential data.
languageNoPreferred code example language. Source URLs and exact versions stay unchanged.
responseNoChoose links to search existing publisher/version metadata without loading, parsing, embedding or saving documentation page contents. Defaults to snippets.
libraryIdYesExact Docsy library ID such as /org/project or /org/project/version.
maxCharactersNoMaximum characters of snippets response including citations; default 6000, max 50000. This is a character cap, not an exact token count.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / maxCharacters / description
      Previous value: -"Maximum characters of snippets response including citation metadata; optional and not an exact token count."New value: +"Maximum characters of snippets response including citations; default 6000, max 50000. This is a character cap, not an exact token count."
  2. Changed2 schema fields changed
    • addedInput schema / properties / language
      Added value: +{
+  "description": "Preferred code example language. Source URLs and exact versions stay unchanged.",
+  "enum": [
+    "TypeScript",
+    "JavaScript",
+    "Python",
+    "Go",
+    "Rust"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / maxCharacters
      Added value: +{
+  "description": "Maximum characters of snippets response including citation metadata; optional and not an exact token count.",
+  "maximum": 50000,
+  "minimum": 1000,
+  "type": "integer"
+}
  3. Changed2 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum number of documentation chunks to return; omit to use the production default."New value: +"Maximum results to return (snippets or links); omit to use the production default."
    • addedInput schema / properties / response
      Added value: +{
+  "description": "Choose links to search existing publisher/version metadata without loading, parsing, embedding or saving documentation page contents. Defaults to snippets.",
+  "enum": [
+    "snippets",
+    "links"
+  ],
+  "type": "string"
+}
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: default snippet budget of 6,000 characters to protect agent context, a 50,000 maximum, the fact that 'links' avoids loading/parsing/embedding page contents, and that maxCharacters is a character cap not a token count.

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?

Four tight sentences, each carrying a distinct decision (scope, response mode, budget, query-count discipline), with the primary constraint front-loaded. No filler or restatement of the name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the work of explaining what each response mode returns, and it covers budget and rate discipline. Minor omissions remain: the default for 'limit', pagination behavior, and the explicit prerequisite of resolving a library ID first.

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 baseline would be 3; the description still earns credit by explaining the semantic tradeoff behind 'response' (links vs snippets) and restating the default/max character budget in context. It adds less on 'limit', 'language', and 'libraryId', which are left to the 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?

States a specific verb (search) and a precisely scoped resource (one resolved library at an exact version, source-linked docs). It explicitly contrasts with the sibling 'search' for unscoped discovery, so an agent can pick between the two without opening either schema.

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?

Gives clear selection guidance between the two response modes ('links' for publisher URLs without page bodies, 'snippets' for excerpts), names 'search' as the alternative for unscoped discovery, and caps effort at 3 focused queries per question. It never explicitly names resolve-library-id as the prerequisite for getting a valid libraryId, which is the one gap.

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

All Docsy toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources