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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the bar is lower, but the description goes well beyond that: it reveals outputs are deterministic committed fixtures, identical on every call, offline, and that a mismatch indicates server drift rather than user error. It also clarifies the structural shape of the response (baseline/current/expected) beyond what the output schema requires.

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?

Every sentence earns its place: the purpose, the scenario content, the no-arg vs id calling convention, the integration loop, and the determinism guarantee are all packed in without redundancy. The critical workflow is highlighted with 'THE LOOP' and front-loaded before secondary details.

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 of this complexity, the description is complete: it explains what the tool returns, how to use it in combination with diff_mappings, the semantic meaning of each parameter, and the determinism/offline guarantees. The output schema and annotations cover the remaining structured details, leaving no critical gap for an agent to call it correctly.

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%, giving a baseline of 3, but the description adds meaningful guidance: it explains that omitting scenario lists all scenarios, and it adds extra context for include_html ('Only useful if you want to render or re-capture it yourself; the loop does not need it'), which helps the agent decide not to set it. This exceeds schema documentation.

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 opens with a specific verb and object: "Get a ready-made selector-drift test case with a known-correct answer." It clearly identifies the resource (DOM captures of deliberately breakable apps with expected verdicts) and distinguishes it from siblings like diff_mappings by positioning itself as the fixture provider in a testing workflow.

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 provides explicit usage instructions: call with no arguments to list scenarios, or with a scenario id to get baseline/current mappings. It then gives a precise multi-tool workflow ('THE LOOP') telling the agent to pass baseline and current to diff_mappings and compare its verdict/counts to the expected result, which is exactly the kind of when-to-use guidance needed.

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