Skip to main content
Glama

Ask fovub's agent about a finished projection

ask_fovub
Destructive

For a projection that check_projection shows done on the user's fovub account: puts one question about the result to fovub's own agent, which answers from the run's shares, method, warning, campaign frames, and sources. The first question opens a block of 10 questions and takes $1 from the user's fovub balance; the block closes after its tenth question, when fovub's Claude cost for it reaches its limit, or an hour after its last question, and the next question then opens a new block for $1. fovub does not disclose how its method works, and its agent says so. Call it only after the user agrees to the price. Needs the user's fovub sign-in.

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": {
      "run_id": "<run_id>",
      "question": "<question>"
    },
    "name": "ask_fovub"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idYesThe run_id that start_projection returned.
languageNoThe user's language as a BCP 47 code, such as es, es-MX, or fr: the language of the user's Claude account, or the language the user writes in. fovub then gives the questions, their choices, and the result's warning in that language. Leave it out for English.
questionYesThe user's question about the result.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only say readOnly=false, destructive=true, idempotent=false; the description goes much further by disclosing the $1 charge per 10-question block, the three ways a block closes (tenth question, Claude-cost limit, one hour idle), the new block/$1 charge afterwards, that the method is deliberately undisclosed, and that the user's fovub sign-in is required. The billing behavior is consistent with destructiveHint=true rather than contradicting it.

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?

Purpose and precondition are front-loaded, then pricing mechanics, then consent and auth requirements. Sentences are long and pricing detail is dense, but each sentence carries operative information an agent needs before spending the user's money.

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 some work on returns by naming the sources the agent answers from, and it fully covers cost, block lifecycle, and auth. It stops short of describing the answer's shape or remaining-question count, which is a minor gap for a paid, non-idempotent call.

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 100% and each parameter carries its own description, including the BCP 47 language codes and run_id provenance. The description reinforces that 'question' is about the result and that run_id comes from a finished run, but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 and resource: it puts one question to fovub's own agent about a finished projection's result, and enumerates the grounding data (shares, method, warning, campaign frames, sources). That is clearly distinguishable from siblings like check_projection (status) and buy_report (deliverables).

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 a firm precondition ('a projection that check_projection shows done') and a hard gating condition ('Call it only after the user agrees to the price'). No alternative tool is named for the not-done case, but the preconditions are explicit enough that an agent knows when not to call it.

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