Skip to main content
Glama

Tomorrow Central: Cloud Cost Sentinel

Record an investigation

webops_record_investigation
Destructive

Records one investigation in the website's log: the question, its kind, the playbook and version, tools called, outcome and what was missing. Feeds new playbooks and data sources. 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>",
      "question": "<question>",
      "kind": "<kind>",
      "playbook": "<playbook>",
      "tools": "<tools>",
      "outcome": "<outcome>",
      "missing": "<missing>"
    },
    "name": "webops_record_investigation"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesThe kind of question in a few words.
toolsYesThe tools called, comma-separated (may be empty).
domainYes
missingYesWhat data would have answered it (empty when nothing was missing; required for cannot_tell).
outcomeYesanswered, cannot_tell or nothing_happened.
playbookYesThe playbook followed, P0–P6.
questionYesThe question as the person asked it (at most 512 characters).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Added

TDQS

A3.7/5.0
Behavior4/5

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

Adds real context beyond annotations: the two-step confirm pattern (returns a summary plus a code for tc_confirm) is critical behavior an agent would otherwise get wrong, and "Changes no website data" scopes the destructiveHint to the investigation log rather than site content. The idempotentHint=false behavior (what happens on repeat calls) is not explained, but the write-avoidance semantics are well disclosed.

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?

Four short sentences, front-loaded with what gets recorded, then purpose, then the critical confirmation caveat. No filler; only the "playbook and version" phrasing is slightly imprecise.

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 the description covers returns (a summary and a confirmation code) plus the required follow-up step, which is the main thing an agent needs. It omits the role of the domain parameter and any failure/duplicate-call behavior, so it is strong but not exhaustive for a 7-required-parameter mutation.

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?

With 86% schema coverage the schema already documents domain, kind, playbook, tools, outcome, and missing, so the baseline is 3. The description's field list largely restates the schema, and its phrase "the playbook and version" introduces a version concept that has no corresponding parameter, which is mildly confusing rather than additive.

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 specific verb and resource ("Records one investigation in the website's log") and enumerates the recorded fields, so the agent knows this is a write of an investigation entry rather than a read. It does not name a sibling such as webops_investigations or webops_investigation_feedback, so disambiguation is left implicit.

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?

"Feeds new playbooks and data sources" implies the downstream purpose and therefore when to log, and the confirmation flow implies a gate. But there is no explicit when-to-use versus when-not, no mention of how this relates to the investigations list or feedback tools, and no prerequisites stated.

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