measure_image

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

The description explains what each metric measures (e.g., tile_seam compares wrap-around join to interior join). However, it does not explicitly state if the tool is read-only or if it requires specific permissions, though this is implied by its measurement nature.

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 relatively concise but uses line breaks and dashes that may not render well in all contexts. It is front-loaded with the main purpose, and each sentence adds value.

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?

Given the existence of an output schema (not described) and no annotations, the description covers the main use case well. However, it does not mention the return type or output schema, and lacks explanation of 'objective test'.

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?

With 0% schema description coverage, the description only adds context for the metric parameter by listing values and meanings. It does not explain the filename or subfolder parameters, leaving them solely to the schema.

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's purpose: 'Score an output objectively' for specific metrics (sharpness, tile_seam, brightness). It distinguishes itself from siblings by focusing on objective measurement for the ratchet system.

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 states when to use: 'Use ONLY where the brief has an objective test' and advises feeding scores to loop_record. Also warns that 'A score is not the judgement' and to use eyes, providing clear context and exclusions.

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