full_audit

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

No annotations exist, so the description carries the full burden. It does disclose the composite nature of the operation, that results are consolidated into a `summary_findings` list, and adds an authorization caveat — real value beyond the schema. However, it never states that this is a read-only, non-mutating operation, nor does it mention cost/latency (a full multi-pass audit on a large binary could be slow) or behavior on unsupported/oversized files.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Dense and front-loaded: the core action and the auto-detection scope land in the first clause, the aggregation detail follows, and the authorization note closes. No filler sentences, though the multi-line enumeration could be tightened slightly.

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

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

For a one-parameter tool with no output schema, the description covers what it does and names the key return field (`summary_findings`), which is decent. Gaps remain around read-only semantics, expected runtime, and output shape beyond the single named field — meaningful for a composite audit that runs four separate analyses.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

A single required `path` parameter with 0% schema description coverage, so the description must compensate. It does partially: 'on a file (auto-detects ELF/PE/Mach-O/APK)' clarifies that `path` is a single file rather than a directory and that format need not be specified. It does not state whether the path is local/absolute or remote, or what happens with unsupported formats.

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

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

States a specific verb+resource ('Run the complete static audit on a file') and enumerates exactly what it aggregates: string extraction, secret scanning, mitigation checks, and APK manifest analysis. Because the constituent scans match the sibling tool names (scan_strings, scan_secrets, scan_binary_mitigations, scan_apk), an agent can immediately tell this is the aggregate superset rather than any single scan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is only implied: the description lists the individual scans, which hints 'use this instead of running the siblings separately,' but never says so explicitly or names when a narrower sibling is preferable. The only explicit directive is a legal/authorization constraint ('Only use on files the caller is authorized to test'), which is a guardrail rather than selection guidance.

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