diffci_select_tests

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: the plan is snapshot-bound, it includes fallback reasons, and crucially the output is advisory rather than a passing result. It does not describe failure modes or what triggers fallback reasons.

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?

Two tightly packed sentences with zero filler; the positive capability is front-loaded and the critical caveat follows immediately. Every clause carries information an agent needs.

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?

With only one optional parameter, no output schema, and read-only annotations, the description covers the essentials and explicitly characterizes the return value. Minor gaps remain around how the plan is scoped (affected tests relative to what baseline) and behavior on a clean working tree.

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% and the single repo parameter is already documented in the schema, including its default. The description adds no additional meaning about how repo affects the diff scope, so the schema is doing the heavy lifting and the baseline of 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 ("Inspect") against a specific resource (staged, unstaged, and non-ignored untracked changes) and names the concrete return artifact: a snapshot-bound affected-test plan plus fallback reasons. It is clearly differentiable from the sibling diffci_run_affected_tests via "Runs no tests," though it never names that sibling outright.

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?

"Runs no tests; a plan is not a passing receipt" gives a clear when-not boundary, steering the agent toward a run/verify tool when actual test execution is required. It stops short of explicitly naming the alternative tool or stating preconditions (e.g., behavior when there are no changes), so it is not a full 5.

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