sbox_run_tests

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states running tests returns pass/fail results, which implies a read-only verification operation. However, it doesn't disclose whether running tests has any side effects, whether it's safe to run concurrently, or how long it might take. The absence of destructive-warning is a gap but not a contradiction.

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 declarative sentence, zero waste. Every word earns its place, covering what it tests (cache, search index, crawler) and what it returns (pass/fail results). Well front-loaded.

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 tool is simple: zero params, no output schema. The description establishes scope and return type. However, it doesn't describe the structure of results (per-test-case breakdown format) or note whether failures are informational or indicate actionable problems. Given the low complexity, this is adequate but could add a note about result granularity.

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?

The tool has 0 parameters, and schema coverage is 100% (trivially, as there are no properties). With zero parameters, there's nothing for the description to explain about input semantics. Baseline 4 applies for a no-parameter tool since description doesn't need to compensate for undocumented params.

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 runs built-in self-tests for cache, search index, and crawler, and returns pass/fail results. The verb 'Run' + resource 'built-in self-tests' is specific, and while it doesn't explicitly distinguish from siblings, its purpose is clear given no sibling does exactly this.

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?

No guidance on when to use this tool vs alternatives. It doesn't mention that this is a diagnostic/verification tool useful for checking system health, nor does it suggest when tests should be run (e.g., after setup, when debugging search issues). No exclusions or alternative tools are named.

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