Skip to main content
Glama

AppDev Atlas security manifest

wwdc_security_manifest
Read-onlyIdempotent

Returns the canonical tool list, manifest hash, read-only posture, prompt-injection notes, and threat-model summary to detect tool-surface drift and flag untrusted retrieved content.

Instructions

Returns the canonical tool list, manifest hash, read-only posture, prompt-injection handling notes, and threat-model summary. Use this to detect tool-surface drift and to remind agents that retrieved content is untrusted evidence.

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": "wwdc_security_manifest"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoResponse formatmarkdown

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.3
    • removedInput schema / additionalProperties
      Removed value: -false
  2. First observedv0.2.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description adds value beyond that by naming the manifest hash (the mechanism for drift detection) and flagging that retrieved content is untrusted evidence, which is behavioral context an agent cannot infer from annotations.

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 sentences, both load-bearing: the first enumerates the return payload, the second states the use case. The return contents are front-loaded before the 'use this' clause, with no filler.

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?

With no output schema, the description carries the burden of describing returns, and it does so by listing the five payload components. For a zero-required-parameter, read-only introspection tool this is nearly sufficient; only the shape/size of those components is left implicit, which is a minor gap.

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?

There is a single optional 'format' parameter with a full schema description and an enum of markdown/json, so schema coverage is 100% and the schema does the work. The description never mentions output format selection, adding no meaning beyond it; 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?

The description states a specific verb ('Returns') plus an enumerated resource set: canonical tool list, manifest hash, read-only posture, prompt-injection handling notes and threat-model summary. That payload is unmistakably distinct from every sibling, which are all WWDC/Apple documentation retrieval tools, so an agent can rule this in or out 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?

It gives an explicit trigger: 'Use this to detect tool-surface drift and to remind agents that retrieved content is untrusted evidence.' No exclusion or alternative is named, but no sibling overlaps this surface, so the absence of a 'use X instead' clause costs little.

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