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

Goes beyond the annotations by disclosing determinism and offline provenance ('committed fixtures, identical on every call'), which reinforces idempotence with concrete reason. It also adds diagnostic semantics not present in the annotations: a verdict mismatch indicates server drift, not bad inputs — context an agent could not infer elsewhere.

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?

Purpose is front-loaded, then the loop, then determinism — a sensible order with labeled segments ('THE LOOP:'). It runs slightly long and the trailing external URL is not needed for correct invocation, though the remainder earns its space.

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?

Covers everything needed for a two-parameter, read-only fixture tool: what it returns (baseline/current mappings), how to use it in a loop, expected semantic ('expected' verdict), and determinism guarantees. With an output schema present, no return-value documentation is missing.

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 coverage is 100%, so both parameters are already documented in the schema, including the 'omit to list' behavior and the include_html caveat. The description restates the no-arg vs. scenario-id behavior but adds no format or syntax detail beyond the schema, so baseline 3 applies.

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 ('Get a ready-made selector-drift test case with a known-correct answer') and scopes the use case ('for testing this MCP server or an agent workflow end to end'). It also implicitly distinguishes itself from diff_mappings by naming that tool as the downstream consumer of its output.

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?

Explicitly covers both call modes ('call with no arguments to list the scenarios; call with a scenario id to get baseline and current mappings') and prescribes the exact follow-up sequence with diff_mappings. It even tells the agent how to interpret a mismatch, removing any ambiguity about what to do with the result.

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