Skip to main content
Glama

ask

Ask the agent. Full pipeline (schema, queries, analysis). Sync within deadline_seconds; else {status:pending,job_id} — poll request_status/read_response. Pass a stable thread id (UUID) on every call for conversation context. The result carries thread_id, the thread actually used; re-send that value on later calls.

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": "ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNoOptional role override; defaults to admin for MCP callers.
agentNoBundle name. Inferred from the Host header when missing.
threadNoPersistent conversation id. Either `thread` or the legacy `thread_id` alias must be set.
messageNoUser prompt for the agent. Either `message` or the legacy `question` alias must be set.
questionNoLegacy apples-compat alias for `message`. Ignored when `message` is set.
thread_idNoLegacy apples-compat alias for `thread`. Ignored when `thread` is set.
publisher_idNoPublisher the research is bound to. Only the dedicated research credential may send it; other callers are refused.
deadline_secondsNoSynchronous wait budget. Default 240.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / publisher_id
      Added value: +{
      +  "description": "Publisher the research is bound to. Only the dedicated research credential may send it; other callers are refused.",
      +  "type": "number"
      +}
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and openWorldHint=true, and the description goes beyond them by disclosing the async fallback return shape {status:pending,job_id}, the polling siblings, and thread persistence semantics. It does not explain that the call may create server-side job/thread state (consistent with readOnlyHint=false) or note auth constraints beyond what the schema says.

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 async behavior, then the thread rule; three compact sentences with no filler. The telegraphic phrasing ("else {status:pending,job_id}") is dense but usable.

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?

With no output schema, the description should carry the return contract, and it only sketches the pending case and thread_id echo; the successful response's shape is never described. For an 8-parameter, open-world, non-idempotent tool, that leaves a meaningful gap.

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 description coverage is 100%, so the schema already documents all eight parameters including the legacy aliases. The description reinforces the most operationally important rule (stable thread id per call, use the returned thread_id) and the deadline_seconds budget, but adds little that the schema lacks.

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

Purpose4/5

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

"Ask the agent" gives a concrete verb and resource, and "Full pipeline (schema, queries, analysis)" scopes what the agent does. It also implicitly separates itself from the polling siblings by explaining that a pending result is retrieved via request_status/read_response. It falls just short of 5 because the domain of the agent (what questions it answers) is never stated.

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?

It states the condition that switches behavior: synchronous when within deadline_seconds, otherwise poll request_status/read_response. It also gives an operational rule for every call (pass a stable thread id, re-send the returned thread_id). No explicit "when not to use" or guidance on choosing deadline_seconds values.

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