Skip to main content
Glama
Sign In

FeatureOS

by io.github.featureos
OverviewDiscussionsAdmin

Delete article

delete_article
Destructive

Permanently delete a knowledge base article. This cannot be undone.

Needs the user's approval: without confirm=true nothing is deleted and the pending change is returned.

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": {
      "article_id": "<article_id>"
    },
    "name": "delete_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoRequired. Set true ONLY after the user has explicitly approved this exact change in the conversation. Without it the tool changes nothing and returns the pending change for the user to approve.
article_idYesThe ID of the article to delete (from list_articles).

Output Schema

NameRequiredDescriptionDefault
successNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is partly structured. The description adds genuine behavioral context beyond that: permanence, no undo, and the confirm gating that yields a pending change instead of a deletion. Only the return shape on success is left to the 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.

Conciseness5/5

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

Two short, front-loaded statements: what it does and the irreversibility, then the approval mechanism. Every sentence earns its place and the highest-risk fact (permanent, no undo) comes first.

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 destructive two-parameter tool with full schema coverage and an output schema, the description covers the critical unknowns: permanence and the approval gate. It does not describe what the pending-change response contains or error cases, but the output schema is expected to carry that.

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 100% and both parameters are fully documented in the schema, including the exact semantics of confirm. The description echoes the confirm requirement without adding format or source details beyond what the schema already states (article_id from list_articles). Baseline 3 applies.

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?

States a specific verb and resource ('Permanently delete a knowledge base article') and immediately flags irreversibility, which separates it from update_article and the rest of the sibling set. An agent can identify the operation 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?

Gives clear usage context in the form of the approval precondition ('without confirm=true nothing is deleted'), so the agent knows how and when to invoke it. It stops short of naming alternatives (e.g., update_article for soft changes), so it is not a full when/when-not statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FeatureOS toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources