Skip to main content
Glama
Sign In

PrismFact

by com.prismfact
OverviewDiscussionsAdmin

Ответ на вопрос — как человеку

prism_answer

Единый порядок слоёв: реестр, вывеска, учреждение, карточки людей, списки города, карта, справочник контактов. Один вопрос — один ответ, тот же самый, что получает человек в боте и на сайте. Списком не отдаётся: карточки людей (что предлагают, что ищут) отвечают только на прямой вопрос, обход закрыт даже здесь — это единственный наш актив, ценность которого мы сами ещё не измерили. Объявления досок в этот инструмент не входят — право на переотдачу не оформлено.

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": {
      "q": "<q>"
    },
    "name": "prism_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesвопрос словами, как человеку
cityNoпо умолчанию Асино

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does a strong job: it discloses that answers are never returned as lists, that people cards can only be answered via direct questions, and that board ads are excluded for legal reasons. It also hints at internal layer ordering, adding context beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is overpacked: it opens with an opaque list of layers and includes a rationale about the unmeasured asset value that does not help an agent invoke the tool. The core behavior is buried in the second sentence.

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?

The description covers selection constraints well but, with no output schema and no annotations, it fails to specify the return format or error behavior. An agent still cannot predict exactly what the 'answer' looks like.

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 q and city. The description only reiterates 'question in words' and does not add format, defaults, or examples beyond the schema.

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?

The description states a clear behavior: one question yields one answer, identical to what a human receives in the bot and website. It also excludes list returns and board ads, which helps distinguish it from list-oriented siblings, though it never names those siblings explicitly.

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

Usage Guidelines3/5

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

It provides implicit usage constraints: use for direct human-like questions, not for list requests, not for people-card bypass, not for board ads. However, it does not explicitly name alternative tools or state a positive selection criterion.

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

All PrismFact 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