run_tests

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

No annotations are present, so the description carries the full disclosure burden. It covers the test file format, the outcome ('report what passed'), and important session lifecycle behavior: opens/closes its own session unless `session` is passed, and leaves the session where the last test finished. It does not disclose failure behavior or output format, but the added session context is genuinely useful and goes beyond the schema.

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?

Four sentences, each earning its place: the main action, the test format, the recommended usage timing, and the session behavior. The primary verb and result are front-loaded, and there is no repetition of schema properties 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?

For a tool with four fully documented optional parameters, the description is close to complete: it explains what a test is, when to run it, and the session side effects. The main gap is 'report what passed' — there is no output schema and no detail about how pass/fail results are presented, though this is a minor omission for a test runner.

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 input schema documents all four parameters with descriptions (100% coverage), so the baseline is 3. The description adds useful background on authoring test files with 5250-do/5250-expect blocks, which helps an agent understand the tool's domain, but it does not add parameter-specific meaning beyond what the schema already provides.

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 and resource: 'Replay screen regression tests against a program and report what passed.' It also distinguishes itself from siblings by explaining the 5250-do/5250-expect Markdown test format and how it relates to screen_do, making it clear this is the batch test-runner rather than an interactive screen tool.

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?

Gives explicit timing guidance: 'Use this after compiling a change... or before making one...' to verify preserved behavior or drive expected screens. It also explains when to reuse a session versus letting the tool open and close its own. It does not explicitly name when-not-to-use alternatives, which keeps it just below a 5.

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