Skip to main content
Glama

Inspect Native Api

inspect_native_api

Analyze a native API boundary in one function by symbol or address to obtain confidence, evidence, jump-table dispatch/data/case mappings, default targets, unsupported branches, and residual unknowns.

Instructions

Analyze a native API boundary in one function identified by symbol or provider-returned address. Returns confidence, evidence, jump-table dispatch/data/case mappings, separately evidenced default targets, unsupported branches, and residual unknowns. Null case values mean unresolved cases, never a known default.

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": {
      "procedure": "main"
    },
    "name": "inspect_native_api"
  }
}

Input Schema

NameRequiredDescriptionDefault
procedureYesA procedure name or address

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-idempotent, closed-world probe, and the description adds substantive behavior beyond that: it enumerates returned fields (confidence, evidence, jump-table dispatch/data/case mappings, separately evidenced default targets, unsupported branches, residual unknowns) and explicitly explains the null-case convention. It does not explain why the operation is neither read-only nor idempotent, so the annotation implication is left unaddressed.

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?

Three tight sentences, purpose first, then return contents, then the null-case caveat, with no filler. The middle sentence is a dense list but each item conveys distinct output semantics.

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?

With no output schema, the description does well to describe the returned evidence structure and null semantics for a complex binary-analysis operation. However, given annotations marking it non-read-only and non-idempotent, it says nothing about cost, side effects, caching, or failure modes for unresolved symbols, which are material gaps for an agent deciding whether to call it.

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 the single parameter is already documented as "A procedure name or address." The description adds only nuance — that the address may be provider-returned — without specifying accepted address syntax, module qualification, or behavior for ambiguous symbols. Baseline 3 is appropriate when the schema carries the burden.

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?

"Analyze a native API boundary in one function identified by symbol or provider-returned address" gives a specific verb and resource, and the "one function" scoping implicitly separates it from the plural, boundary-level sibling inspect_managed_native_boundaries. It is clear what the tool produces, but it never names a sibling tool to contrast against.

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 only implied: the agent learns this is for a single function's API boundary and that the input can be a provider-returned address, which hints at a follow-on workflow after address resolution. There is no explicit when-to-use versus inspect_native_dispatch_metadata or inspect_native_instruction, and no stated prerequisites or exclusions.

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