Skip to main content
Glama

Inspect Keyed Archive

inspect_keyed_archive
Idempotent

Inspect an NSKeyedArchiver plist in an app bundle as original object-table nodes, class descriptors, roots, and UID edges while preserving shared and cyclic references without instantiating classes.

Instructions

Inspect one Foundation NSKeyedArchiver plist in the active app bundle as original object-table nodes, class descriptors, named roots, and UID edges. Preserves shared and cyclic references without instantiating classes. The path is relative to the bundle; root selection and object pagination preserve original identities.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "Contents/Resources/Model.plist"
    },
    "name": "inspect_keyed_archive"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoLocal filesystem path used by this operation.
rootNo
limitNo
offsetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Goes beyond the annotations in a genuinely useful way: it discloses that classes are never instantiated and that shared/cyclic references are preserved, which tells the agent the inspection is non-destructive to the object graph and lossless. It also warns that pagination and root selection preserve identity, so sliced output can be correlated. The only gap is that annotations decline readOnlyHint while the description reads as a pure inspection with no stated side effect, leaving the mutation profile slightly ambiguous.

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?

Three dense sentences with the object of inspection front-loaded and no filler. Each clause carries information: what is inspected, what is preserved, and how the path/paging behave.

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 usefully enumerates the returned structures (object-table nodes, class descriptors, named roots, UID edges), which is the key completeness item for a read/inspect tool. Remaining gaps are minor: no error behavior for a path outside the bundle and no note on the 20000 object cap.

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 only 25% (only path is documented, and generically), so the description must compensate; it does partially by stating the path is relative to the bundle, and by labeling root as 'root selection' and limit/offset as 'object pagination'. It still never explains what a valid root value looks like, what happens when root is omitted, or that limit is capped at 20000.

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?

Names a precise verb and resource: inspecting a single Foundation NSKeyedArchiver plist inside the app bundle, and enumerates exactly what is produced (object-table nodes, class descriptors, named roots, UID edges). The domain specificity (NSKeyedArchiver plist, not an engine archive or asset catalog) makes it distinguishable from the inspect_* siblings without opening their schemas.

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 rather than stated: 'in the active app bundle' and 'the path is relative to the bundle' tell the agent where the target must live, and the pagination sentence hints at how to traverse large archives. There is no explicit when-to-use/when-not guidance and no named alternative for other archive types, so the agent must infer the boundary from the noun phrase alone.

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

Deploy Server

Other Tools