get_test_metadata

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

No annotations are provided, so the description carries the full burden. It clearly states what is returned, and the verb 'Returns' implies a read-only operation. However, it does not disclose any potential behavioral details such as network download when the trace_path is a URL, time costs, or error handling. This is a minor gap given the simplicity of the tool.

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?

The description is a single, focused sentence with no redundant information. It lists the return fields efficiently and is easy to parse at a glance.

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 simple metadata retrieval tool with one well-documented parameter and no output schema, the description is complete. It explains exactly what the tool returns, and the schema covers the input. No additional context is necessary.

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 single parameter trace_path has 100% schema description coverage, explaining it accepts a path or URL. The tool description adds context about what fields will be returned but does not add any additional parameter-specific semantics beyond the schema. Baseline 3 is appropriate.

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 verb 'Returns' plus the resource 'test metadata' clearly states what the tool does. Enumerating the exact fields (title, browser, platform, viewport, start time) distinguishes it from sibling tools like get_trace_summary or get_element_state_at_failure.

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 the tool is used when you need basic test metadata (title, browser, etc.), but it does not explicitly state when to use it over alternatives or mention exclusions. There is no guidance about when not to use this tool, unlike the get_calls example which names a sibling alternative.

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