squire

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

Discloses execution environment ('fresh disposable sandbox') and scope ('bounded'), but lacks critical behavioral details required in absence of annotations: output format, sandbox lifecycle, side effects, or failure modes. No indication of what constitutes job success/failure.

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?

Single sentence of 10 words with high information density. Every element serves a purpose: verb, scope, technology constraints, and execution environment. No redundancy or filler.

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 complexity (execution tool, 4 params, no annotations/output schema), the description covers the essentials but leaves gaps. Adequate for invocation, but missing behavioral details regarding return values, persistence, or sandbox teardown that would make it complete.

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 100% schema coverage, baseline is 3. The description adds valuable domain context: 'Z3 or MiniZinc' clarifies valid 'solver' values, 'bounded' contextualizes the timeout parameter, and 'jobs' frames the file/data parameters' purpose.

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?

Specifies exact action ('Run'), resource type ('solver jobs'), and valid inputs ('Z3 or MiniZinc'). The 'fresh disposable sandbox' adds execution context. However, it does not explicitly differentiate from potentially related siblings like 'verify' or 'quantum_simulate'.

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?

Implies usage context through 'bounded' (suggesting time/resource constraints) and specific solver technologies. However, lacks explicit when-to-use/when-not-to-use guidance or comparison to alternatives like 'compile' or 'verify'.

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