Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

oto_doc_app

Rendered docs browser (MCP App / interactive card) — READ ONLY.

Visual variant of oto_doc that renders pages INLINE instead of returning JSON. WITHOUT arguments = the tree of the active org's HISTORICAL docs project (whatever it is named — resolved by its anchor); pass project_id to browse the docs of the project you actually mean. With project_id = that project's pages tree (children indented under parents). With doc_id = ONE page, markdown rendered. With query (+ optional project_id) = full-text hits with snippets, accent-insensitive.

Use when the user wants to see a page or explore a project's docs without leaving the chat. The text result gives YOU the same content (the whole page, the tree, the hits) — read it, never summarize from the card. For raw JSON or ANY write (create/update/move/share), use oto_doc.

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": "oto_doc_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNofull-text search in the project's pages (title + body).
doc_idNorender ONE page (title + markdown body). Takes precedence.
project_idNoproject whose pages to browse ; omit = the active org's historical docs project (resolved by its anchor).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden — and it does declare READ ONLY up front, explains that the default project is resolved by an anchor rather than by name, notes that doc_id takes precedence over query, and warns the agent to read the text result rather than summarize the card. It does not cover permissions or any size/pagination limits on the rendered tree or hits, which is the remaining gap for a no-annotation tool.

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-loads the READ ONLY constraint and the tool's identity, then enumerates the three argument modes as parallel clauses. Dense but every clause is functional; the parenthetical asides ("whatever it is named — resolved by its anchor") are wordy but prevent a real mistake.

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?

All optional params, no output schema, and the description still covers the return-channel question by explaining that the text result carries the same content as the card and that the agent must read it. For a read-only three-param viewer with a sibling to route against, 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 adds precedence and combinatorics the schema does not: doc_id wins, query accepts an optional project_id, omitting everything targets the active org's historical docs project regardless of its name. That is meaningful added semantics beyond the per-parameter blurbs.

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 + resource ("Rendered docs browser ... renders pages INLINE instead of returning JSON") and immediately demarcates the sibling: oto_doc is for raw JSON or any write. 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use ("Use when the user wants to *see* a page or explore a project's docs without leaving the chat") and explicit when-not ("For raw JSON or ANY write (create/update/move/share), use `oto_doc`"). It also spells out which argument combination produces which mode, which is the real routing decision here.

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

All Tulina toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources