squire

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

With no annotations provided, the description carries the full disclosure burden. It valuably mentions 'clean runtimes' (isolation) and 'target matrix' (execution model), but fails to disclose critical execution traits like side effects/destructiveness, blocking behavior, or what constitutes success/failure return values.

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 16-word sentence with zero waste. Every phrase earns its place: 'small or medium' defines scope, 'clean runtimes' defines environment, 'target matrix' defines execution pattern, and the language list defines supported platforms. Front-loaded with the primary action.

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?

Adequate for a 5-parameter tool with complete schema coverage, but the lack of output schema means the description should ideally hint at return behavior (test results, pass/fail signaling). The description successfully covers input intent and execution environment but omits output/completion semantics.

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?

Despite 100% schema coverage (baseline 3), the description adds significant semantic context: 'target matrix' explains the execution model for the 'targets' parameter, 'clean runtimes' describes the execution environment, and 'Python, Node, or Bash' reinforces valid language inputs. This contextual layer meaningfully augments the schema definitions.

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 verb 'Run' and resource 'test jobs' with specific scope modifiers ('small or medium', 'clean runtimes') and supported languages ('Python, Node, or Bash'). It implicitly distinguishes from siblings like 'build' or 'compile', though it doesn't explicitly differentiate from similar testing tools like 'verify' or 'bench'.

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 description provides scope guidance ('small or medium test jobs') implying suitability boundaries, but lacks explicit when-not-to-use guidance or named alternatives. With siblings like 'verify', 'bench', and 'audit' present, the absence of explicit differentiation guidance is a notable gap.

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