MiSTerClaw

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

Strong disclosure despite no annotations: explains return format ('raw hex data and decoded option values'), provides example output ('Aspect Ratio = Original'), and describes data semantics ('per-game/core settings as bit fields'). Could improve by mentioning error conditions or caching behavior.

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?

Three well-structured sentences with zero waste: action definition, return value specification, and data format context. Appropriately sized for a single-parameter read tool.

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?

Adequately complete for low complexity: describes return values (compensating for missing output schema), explains the bit-field storage mechanism, and clarifies the per-game scope. Could mention error states or empty core scenarios.

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 coverage is 100%, establishing baseline 3. Description reinforces the parameter's purpose by mapping 'core' to 'running core/game', but does not add validation rules, format constraints, or examples beyond what the schema already provides.

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?

Excellent specificity: 'Read' (verb) + 'CFG file' (resource) + 'for the running core/game' (scope). Clearly distinguishes from sibling mister_cfg_write (read vs write) and unrelated tools like mister_info or mister_status by explicitly naming the CFG file domain.

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?

Provides implied usage context by describing the 'running core/game' default behavior and contrasting with the write sibling through the action verb 'Read'. However, lacks explicit when-to-use guidance comparing against mister_cfg_write or stating prerequisites like requiring a loaded core.

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