Skip to main content
Glama

Ask a shared document

ask_shared

The parts of a shared document that answer one question, in the user's words. The sender sees each question. Confidential under the sender's rules.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "link": "<link>",
      "question": "<question>"
    },
    "name": "ask_shared"
  }
}

Input Schema

NameRequiredDescriptionDefault
linkYesThe ArtifactSend link the user shared, e.g. https://artifactsend.com/d/ab12cd34 or /r/... for a data room.
documentNoFor a data room: which document, by its title or id from open_link. Leave out for a single document.
questionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.1/5.0
Behavior4/5

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

The description discloses a genuine side effect that the annotations only hint at: "The sender sees each question," which explains why readOnlyHint is false despite this looking like a read. It also adds the confidentiality framing the annotations do not carry. It stops short of stating retention, whether questions are logged permanently, or what happens when no answer exists.

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?

Three short sentences, front-loaded with what is returned and followed by the disclosure that matters most. Nothing is wasted, though the phrasing is elliptical enough ("in the user's words") that it trades some clarity for brevity.

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

Completeness3/5

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

For a 3-parameter tool with no output schema, the description covers purpose and the key social side effect but omits what the response contains (citations? excerpts? 'no answer found' behavior) and how it interacts with data rooms beyond what the schema says. Adequate rather than complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% and the schema already explains link and document thoroughly; the undescribed 'question' parameter gains some meaning from "one question, in the user's words," clarifying single-question scope and natural-language phrasing. That is a marginal addition over the schema, not a compensating one.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description says it returns "the parts of a shared document that answer one question," which conveys a retrieval/Q&A purpose, but the verb is implicit and no explicit action (ask, query, search) is named in the text itself. Crucially, it never distinguishes this from siblings like read_shared, open_link, or list_questions, so an agent cannot tell which to pick without external inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

There is no statement of when to use this versus read_shared or open_link, and no prerequisites beyond a vague implication that a link has been shared. "Confidential under the sender's rules" hints at a constraint but is too elliptical to function as usage guidance.

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