Skip to main content
Glama

Client: record a verdict on a ledger line

expectation_verdict
Destructive

The client's expectations ledger: every change and the result it should bring, checked on a date with a pass/fail rule. Records a verdict by hand on one line (manual lines on their date, or overriding one): met, partial, missed or inconclusive, with the number and one line why. cancelled closes a line that no longer applies; cancelling the open line of a recurring one ends it.

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": {
      "client": "<client>",
      "id": "<id>",
      "verdict": "<verdict>",
      "why": "<why>"
    },
    "name": "expectation_verdict"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesthe line
whyYesone line, with the number
valueNothe number at the check
clientYesClient name from list_clients
verdictYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotent=false, and the description adds genuinely new behavior: that it overrides an existing verdict, and that 'cancelled' closes a line while cancelling the open line of a recurring expectation ends the recurrence. That is exactly the destructive side-effect detail an agent needs beyond the flags; only the override/irreversibility of prior verdicts is left implicit.

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

Conciseness3/5

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

Dense and information-rich with no filler, but the ledger framing occupies the front position while the actual action sits in the second sentence, so it is not optimally front-loaded. The parenthetical clause is packed tightly enough to require a second read.

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?

No output schema exists and this is a destructive mutation, yet the description covers verdict semantics, override behavior, and cancellation consequences, which is most of the burden. It stops short of stating whether a verdict can later be changed back or what happens to a recurring line's prior verdicts.

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 80% so the baseline is 3, but the description goes further by pairing 'the number' with value and 'one line why' with the why field, and by enumerating the four pass/fail outcomes plus cancelled with their meanings. That adds real semantic meaning to the otherwise bare enum.

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?

Second sentence states a specific verb (records) on a specific resource (a verdict on one ledger line) and names the valid outcomes, so an agent can separate this from expectation_add/expectations_list. The leading sentence about the ledger is context rather than purpose, but it does not obscure what the tool does.

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?

'Records a verdict by hand on one line (manual lines on their date, or overriding one)' implies the when, and the cancelled clause explains a distinct mode, but there is no explicit statement of when to use this rather than expectation_add or expectations_list, and no prerequisites (e.g., whether the line must already exist).

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.