get_test_results

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

Beyond readOnlyHint, the description adds context about being a legacy facade and that without run_id it may read a stale latest run. This is useful behavioral info, but it doesn't disclose return format, error behavior, or relationship to newer tools. No contradiction with annotations.

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 only two sentences and not verbose, but 'Legacy result facade' is jargon-laden and under-specified. It's concise in length but not necessarily well-structured for clarity; the first sentence adds little value.

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?

Given the tool has no output schema and sits among many test-related siblings, the description doesn't explain what the results look like, how it differs from get_test_run, or why it's legacy. The missing run_id parameter and lack of return-type info leave significant gaps.

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?

Description instructs to 'Pass run_id' but the input schema is an empty object with zero parameters. This creates a direct conflict: the parameter it references doesn't exist in the schema, so an AI agent cannot know how to supply run_id. This is misleading and fails to clarify parameter semantics.

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 labels the tool as 'Legacy result facade' but doesn't state a clear verb or resource. It implies retrieval of test results via 'prevent reading a stale latest run', but it's vague and doesn't distinguish from sibling tools like get_test_run. The purpose is inferable from the name but not clearly articulated.

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 only guidance is that passing run_id avoids stale reads, but it doesn't say when to use this tool instead of alternatives like get_test_run or run_tests. The 'Legacy' label hints at deprecation but no alternative is named.

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