Check Hara source

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable context: the check is 'bounded', runs in a 'fresh restricted pure sandbox profile', and returns 'structured diagnostics'. This goes beyond the annotations, though the 'same sandbox profile' reference is slightly ambiguous without knowing what it is the same as.

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?

A single, dense sentence that front-loads the action, enumerates the check types, and conveys the key context (bounded, fresh sandbox, structured diagnostics) without wasted words. Every clause adds meaningful information.

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?

The description covers the core purpose, check types, sandbox environment, and output nature, and an output schema exists to explain return values. However, it omits the semantics of the `limits` parameter, gives no guidance on error/failure behavior, and the 'same fresh restricted pure sandbox' phrasing is unclear without additional context.

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 description coverage is 0%, so the description needed to compensate, but it only mentions 'bounded' without explaining the `limits` object or its wallMs/outputBytes fields. It does restate the profile enum values, but those are already present in the schema. The `source` parameter semantics are implied by the title, not detailed.

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 uses a specific verb ('Run') and resource ('check' on Hara source), enumerates the exact check varieties (reader, compile, namespace, lint, test), and clarifies the sandbox context and output type. This clearly differentiates it from sibling tools like hara_eval or hara_call by emphasizing diagnostics-producing checks.

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 implies when to use this tool: whenever a bounded compile/lint/test/namespace/reader check is needed. However, it does not explicitly state when not to use it or name alternatives like hara_eval or hara_call, leaving the decision to the agent's inference.

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