Skip to main content
Glama

Tallyho

Report what happened

report

Report on a booking, by booking_id, from any session. After the call to the plumber: result confirmed, declined or not_booked, plus the quote (price, slot). After the job: completed, not_completed, no_show or a cancellation, plus the final price and arrival time. Verdicts per promise are kept, broken or unobserved; Tallyho computes price and timing verdicts from the figures. Kept and broken are final. Returns the plumber's updated likelihoods and, if the booking fell through, the next best plumbers from the same search.

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": {
      "booking_id": "<booking_id>"
    },
    "name": "report"
  }
}

Input Schema

NameRequiredDescriptionDefault
quoteNoWhat the business quoted. Lets Tallyho compute the price and slot verdicts.
actualNo
resultNoWhat happened to the booking. Moves it to this status.
verdictsNokept, broken or unobserved, per promise in scope
booking_idYes

Output Schema

NameRequiredDescriptionDefault
statusYes
ignoredYes
recordedYes
booking_idYes
environmentYes
alternativesYes
business_nowYes
contract_versionYes
still_unobservedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Beyond the annotations (which only say it is not read-only, not idempotent, not open-world, not destructive), the description adds real behavioral facts: kept/broken verdicts are final and irreversible, Tallyho derives price and timing verdicts from the supplied figures, and the call returns updated plumber likelihoods plus fallback candidates. It could still be clearer about re-reporting an already-final booking.

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 core action and booking_id, then layered by lifecycle stage (quote, job, verdicts, return). The telegraphic sentence fragments ('Kept and broken are final.') are dense but each carries information; nothing is padding.

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?

For a five-parameter mutation tool with nested objects and an output schema, the description covers lifecycle timing, verdict semantics, irreversibility, and what the call returns. The remaining gap is whether omitted verdicts or the actual block may be skipped, which the description never clarifies even though the schema marks only booking_id as required.

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?

With schema coverage at 60%, the description fills meaningful gaps: it explains that the quote bundle is price plus offered slot, that the actual bundle is final price and arrival time, and that verdicts are supplied per promise as kept/broken/unobserved while price and timing verdicts are computed rather than passed. It does not state which parameters are optional versus required at call time, leaving the agent to read the schema for that.

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 concrete verb and resource — reporting the outcome of a booking identified by booking_id — and enumerates the exact outcome vocabulary (confirmed/declined/not_booked vs completed/not_completed/no_show/cancelled). It does not explicitly differentiate itself from the sibling 'status' tool, so an agent must infer that this one writes state while the other likely reads it.

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?

Usage context is given in lifecycle terms: use it 'after the call to the plumber' for quote-stage outcomes, and 'after the job' for completion-stage outcomes, which tells an agent which fields to supply when. 'From any session' also reassures the caller no session context is required. No explicit when-not guidance or named alternative is provided.

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