Skip to main content
Glama

Tomorrow Central: Cloud Cost Sentinel

Rate an investigation's answer

webops_investigation_feedback
Destructive

Records the person's verdict on one recorded investigation's answer (helpful, not helpful or wrong) and why. It changes no website data. Nothing happens until the person confirms: this returns a summary and a code for tc_confirm.

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": {
      "domain": "<domain>",
      "investigation_id": "<investigation_id>",
      "verdict": "<verdict>",
      "note": "<note>"
    },
    "name": "webops_investigation_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteYesWhy (may be empty).
domainYes
verdictYeshelpful, not_helpful or wrong.
investigation_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Added

TDQS

A3.8/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing the two-step flow: the call returns a summary plus a code for tc_confirm, and nothing is committed until the person confirms. It also scopes the write ('changes no website data'), which contextualizes destructiveHint=true as a feedback-store write rather than a site mutation. It does not say whether a verdict can be re-submitted or replaced, which matters given idempotentHint=false.

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

Conciseness5/5

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

Two short sentences, front-loaded with the action and verdict set, followed by the confirmation semantics. No filler and nothing repeated from the schema.

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?

There is no output schema, and the description compensates by explaining what the return contains (a summary and a tc_confirm code). For a four-required-parameter write tool it covers effect, safety scope and next step; only the identity/format of domain and investigation_id is left unaddressed.

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 50%: verdict and note are self-documented, and the description usefully restates the three verdict values and that the note is the 'why'. It adds nothing about domain or investigation_id, both of which are undescribed in the schema, so the coverage gap is only partly compensated.

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?

States a concrete verb (records) and a precise resource (a person's verdict on one recorded investigation's answer), and enumerates the verdict values. It implies separation from webops_record_investigation by scoping itself to rating an answer on an already-recorded investigation, but never names that sibling 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?

Usage is implied: call this after an investigation exists and the person has formed an opinion on its answer. The confirmation flow ('nothing happens until the person confirms') hints at the ordering but there is no explicit when-to-use/when-not statement or named alternative for capturing feedback that is not about an investigation answer (e.g. report_feedback).

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