Skip to main content
Glama

Answer a defence prompt by hand

defend

Answer the open defence prompt by hand (the SDK answers it with the plain default when you do not): { success, refused, forkSave, choice: "inner"|"outer" } as the prompt allows.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "defend"
  }
}

Input Schema

NameRequiredDescriptionDefault
choiceNowhich of the two the prompt offers to keep: inner or outer
refusedNotrue to refuse the defence, where the open prompt allows it
successNotrue to answer that the defence succeeds, where the open prompt allows it
forkSaveNotrue to use the fork’s save, where the open prompt offers one

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / choice / description
      Added value: +"which of the two the prompt offers to keep: inner or outer"
    • addedInput schema / properties / forkSave / description
      Added value: +"true to use the fork’s save, where the open prompt offers one"
    • addedInput schema / properties / refused / description
      Added value: +"true to refuse the defence, where the open prompt allows it"
    • addedInput schema / properties / success / description
      Added value: +"true to answer that the defence succeeds, where the open prompt allows it"
  2. First observed

TDQS

B3.1/5.0
Behavior3/5

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

Annotations only declare readOnly=false, destructive=false, idempotent=false, openWorld=false, leaving room for the description to add value. It does add one useful behavior: if the tool is not called, the SDK answers with the plain default, and options are gated by what the prompt permits. It does not say what the tool returns on refusal, whether choices are reversible, or what the default answer actually is.

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?

A single sentence, front-loaded with the action, with no filler prose. It loses a point because embedding the literal '{ success, refused, forkSave, choice: "inner"|"outer" }' signature restates the schema and makes the sentence hard to parse on first read.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Four optional parameters, no output schema, and no annotations covering side effects means the description carries real weight. It covers argument intent and the default-answering fallback but says nothing about what calling the tool returns or what state changes a 'defence' answer causes, which is the key missing piece for an agent.

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%, so all four parameters are already documented with per-field descriptions and an enum, making 3 the baseline. The description duplicates the field list rather than adding meaning; the only genuine addition is the qualifier that each option applies only 'where the open prompt allows/offers', which is marginal beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a verb and resource ('Answer the open defence prompt by hand') and even sketches the expected argument payload, so the basic action is identifiable. However, domain terms like 'defence prompt', 'fork's save', and 'inner'/'outer' are never grounded, so an agent cannot tell what this tool actually operates on. It also hints that an SDK default exists but never names a sibling tool as the alternative.

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?

The parenthetical '(the SDK answers it with the plain default when you do not)' implies the tool is only needed when deviating from the default, which is real when-to-use guidance. The repeated 'as the prompt allows' / 'where the open prompt allows/offers' clauses hint that availability is conditional. Neither point is explicit about prerequisites or what to do when the prompt does not offer an option.

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