audit_script

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

With no annotations, the description carries the behavioral disclosure burden. 'Scan' suggests a read-only static analysis, and the examples make the behavior concrete, but it never explicitly states whether the file is modified, what the return value looks like, or whether external resources are needed. This is adequate but not fully transparent.

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?

The description is a single, front-loaded sentence with no filler. Every element earns its place: the action, the accepted file types, the purpose, and concrete examples of issues detected.

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, this description is mostly sufficient to invoke it, but the absence of an output schema and annotations leaves the return format and side-effect profile unspecified. An agent knows what to scan, but not precisely what to expect back or whether the operation is safe.

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?

The schema already describes 'path' as 'Path to the script file to audit', so the baseline is 3. The tool description adds meaningful file-type constraints by specifying .pwn or .inc scripts, which is useful context not present in the schema itself.

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?

The description states a specific action ('Scan'), a clear resource ('.pwn or .inc script'), and concrete examples of what it finds ('Large arrays, Hardcoded IDs'). It is clear enough to distinguish from reading or compiling scripts, though it does not explicitly contrast with the closely named sibling audit_performance.

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?

The purpose statement implies this tool is used when an agent needs to audit a Pawn script for issues, but there is no explicit when-to-use or when-not-to-use guidance, and no mention of alternatives like audit_performance or read_pawn_script. The usage context is present only by implication.

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