Skip to main content
Glama

Ask the bot in the test chat

dosai_test_bot

Send one test message to the bot as if a client wrote it and get the bot's reply; that is all this tool does. A dry run: the bot's functions (booking, owner notifications, Google Sheet, the owner's webhook, invoices) are only simulated, so nothing is sent, booked, written or billed and no client gets anything; tool_calls lists which of them the bot would have used. Only reading is live (free time slots, sheet rows), so the reply is realistic. Pass the earlier turns in history to continue a conversation. Costs a few cents from the project balance. Use it to check an answer after changing the prompt, the knowledge base or a function.

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": {
      "project_id": "<project_id>",
      "message": "<message>"
    },
    "name": "dosai_test_bot"
  }
}

Input Schema

NameRequiredDescriptionDefault
historyNoEarlier turns of this test conversation, oldest first.
messageYesWhat the client writes.
project_idYesFrom dosai_list_projects.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / project_id / description
      Previous value: -"Project id, as returned by dosai_list_projects."New value: +"From dosai_list_projects."
  2. Changed1 schema field changed
    • removedInput schema / properties / project_id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Well beyond the annotations, it enumerates exactly which simulated side effects occur (booking, owner notifications, Google Sheet, owner webhook, invoices) and guarantees nothing is sent, booked, written or billed, while disclosing that reads are live and that a call costs a few cents from the project balance. It also explains the tool_calls field, a return detail no structured field covers since there is no output schema.

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 the action, then the dry-run guarantee, then the cost and the trigger, which is the right order of importance. It is dense and semicolon-joined, and the aside 'that is all this tool does' is mildly redundant next to the explicit enumeration of simulated functions, but nothing is wasted.

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?

For a 3-parameter tool with no output schema, it covers the safety model, the live-vs-simulated read split, the cost, multi-turn continuation and the shape of the result (tool_calls). Nothing an agent needs in order to call it correctly or interpret the reply is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, and the description earns an extra point by explaining the operational meaning of history — 'Pass the earlier turns in history to continue a conversation' — which tells the agent how to maintain multi-turn state rather than just what the array contains.

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?

The opening clause names a specific verb and resource — 'Send one test message to the bot as if a client wrote it and get the bot's reply' — and the follow-up 'that is all this tool does' fences the scope so it cannot be confused with dosai_send_test_notification or dosai_test_integration. An agent can select it without opening the schema.

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 gives a concrete trigger condition: 'Use it to check an answer after changing the prompt, the knowledge base or a function.' That is clear positive guidance, but it never states when not to use it or names the sibling to pick instead (e.g. a real send vs a simulated one), leaving that inference to the agent.

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