classify_asset

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

No annotations are present, but the description explicitly states 'No writes', making the read-only nature clear. It also discloses that it analyzes filename patterns and content edge-periodicity, and returns a classification with tier/op/category/flags. This provides substantial behavioral insight beyond what schema offers.

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 moderately long but every sentence adds useful information—detection logic, edge-case detection, outputs, and side-effect guarantee. It front-loads the main action, though it could be condensed.

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?

With no output schema, the description partially compensates by listing returned fields (tier, op, category, flags). It doesn't enumerate possible tier/category values, but for a classification tool with a single input, this is reasonable completeness.

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?

Schema covers 100% of the single parameter with a clear description of filePath. The tool description doesn't add much parameter-specific detail beyond what the schema already states; it repeats the PNG context. Baseline 3 is appropriate.

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 clearly states the tool inspects a PNG before import and determines if it is a native RMXP asset, going beyond canvas dimensions. It specifies detection methods (filename fingerprinting, edge-periodicity) and distinguishes itself from generic validators by targeting RMXP-specific tile-size issues.

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?

Explicitly says 'before import', which is the appropriate usage context. It also explains the value (detecting 1.5x/2x size mismatches). However, it doesn't explicitly contrast with sibling validate_assets or state when not to use it, leaving some ambiguity.

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