run_tests

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful context that execution happens in an isolated sandbox or disposable copy and that output is 'bounded evidence', but never explains what bounded means, timeouts, or failure behavior. This extra context earns above baseline without being rich.

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 verb and outcome, with no wasted clauses. Slightly overloaded with environment detail but efficient overall.

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?

No output schema and 0% parameter coverage mean the description must carry more weight, but it omits parameter meanings, result format, and failure/timeout behavior. Assertions like 'bounded evidence' are unexplained, leaving real gaps for an execution tool.

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% across four parameters (scope, runner, timeout, repo_path), so the schema explains nothing. The description compensates only weakly: 'detected ... test suites' hints at runner auto-detection but scope, timeout, and repo_path semantics are entirely absent.

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?

States a specific verb (runs) and resource (detected project-native test suites) with execution environment detail (sandbox worker or disposable local copy). It is distinguishable from nearby tools like test_plan, though it never names the sibling explicitly, so it falls just short of a 5.

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 gives no guidance on when to use this tool versus test_plan or other analysis tools, and no prerequisites or exclusions. The agent must infer usage from the name alone.

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