replay

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

Description discloses that the tool automatically opens a browser (with option to disable via no_browser parameter) and shows a diff. No annotations exist, so description carries full burden; it adequately covers key behaviors.

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?

Three sentences, front-loaded with core purpose, concise and no wasted words.

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?

Adequately explains outcome (HTML report opened in browser) despite no output schema. Does not mention prerequisites (e.g., test must exist) but sufficient for simple 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?

Input schema has 100% description coverage, so baseline is 3. The description adds minimal semantic value beyond schema descriptions (e.g., confirms open behavior).

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?

Description clearly states the tool opens a trajectory diff viewer for tests, showing side-by-side HTML comparison. This distinguishes it from siblings like compare_agents or run_test.

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 explicit guidance on when to use replay vs alternatives like compare_agents or list_tests. Usage is implied but not contrasted with sibling tools.

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