Skip to main content
Glama

Buy a finished projection's sources

buy_sources
Destructive

For a projection that check_projection shows done on the user's fovub account: takes $3 from the user's fovub balance, once for the run, and returns the run's sources: for each person, each topic group of campaign activities with the links fovub pulled and the evidence it took from each, so the user's own AI agent can open the links and work over them. The sources hold no feature name, value, score, or weight. A second call for the same run returns the sources free. 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>"
    },
    "name": "buy_sources"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idYesThe run_id that start_projection returned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations: exact price ($3), one charge per run rather than per call, repeated calls for the same run are free, sign-in requirement, and the boundary that returned sources contain no feature name, value, score, or weight. The only tension is the $0 repeat call against idempotentHint=false, but that hint plausibly reflects the one-time billing event, not a stated contradiction.

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 price and the completion precondition, and the trailing sentences each add a distinct fact (return shape, content boundaries, free repeat, consent gate, auth). The middle sentence is dense and long, but no sentence is filler.

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?

With no output schema, the description still specifies the return shape well enough (per-person topic groups, links, per-link evidence, and explicitly absent score/feature fields). Cost, consent, auth, and repeat-call behavior are all covered for a paid mutation tool.

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 the sole parameter run_id is fully documented there, so the schema carries the semantics. The description only reinforces that the run must already exist and be complete, adding marginal meaning beyond 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 concrete verb and resource: it charges $3 to a user's fovub balance and returns a finished run's sources, described structurally (per person, per topic group, links plus extracted evidence). That is clearly separable from check_projection (status check), buy_projection, and buy_report (other purchasables).

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 an explicit precondition ('for a projection that check_projection shows done on the user's fovub account') and an explicit gate ('call it only after the user agrees to the price'), naming check_projection as the gating sibling. The agent has both the when and the when-not without inference.

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