Xdist Apply

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the agent knows this is a mutating, non-idempotent operation. The description adds useful context about the execution mechanism (pre-commit run --hook-stage <stage> and what heavy hooks include), but it never discloses the actual write behavior it performs — rewriting pre-commit configs across ~40 repositories — nor the default-dry-run safety posture, both of which appear only in the schema's parameter text. No contradiction with annotations, but the headline prose omits the mutating nature.

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 short paragraphs, reasonably front-loaded, but the second paragraph largely restates the stage mapping that the schema already provides, and the text carries formatting artifacts (doubled backticks, the leading "(rm_gates)" parenthetical). It is not bloated, but several sentences do not earn their place because they duplicate structured data.

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 12-parameter tool with zero required parameters and an output schema, the description omits what an agent most needs: what the tool actually changes, how an action is selected (no action parameter is present), which parameters matter for which action, and the deliberate dry_run=True default. Output handling is covered by the output schema, so that omission is fine, but the behavioral/config-rewrite gap is significant for a tool this broad.

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 description coverage is 100%, so the schema already documents all 12 parameters and the baseline of 3 applies. The description's stage discussion duplicates the stage parameter's own schema description rather than adding new meaning, and it offers nothing for repo/fleet/repos/top_n/threads/timeout/escalate. The action-selection hints scattered across the parameters ("'status'", "'retest'", "'xdist_apply'") are never reconciled by the description, which leaves ambiguity about how an action is chosen.

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 names a verb and resource ("Run and inspect the two-tier (fast/heavy) pre-commit gate across repos") and explains what each stage exercises, so the domain is legible. However, it reads as a module-level docstring for the whole rm_gates family rather than naming this tool's specific job: the tool is named "xdist_apply" (and the only place the apply/config-rewrite semantics appear is inside the dry_run parameter description), while the prose describes generic gate running that siblings like rm_gates_run and rm_gates_retest would also claim. No sibling differentiation is offered.

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?

There is no when-to-use guidance relative to the many sibling gate tools (rm_gates_run, rm_gates_retest, rm_gates_status, rm_gates_profile, rm_gates_audit_fail_fast), and no prerequisites or exclusions. The claim that it is "the single tool that can actually drive both tiers" is a differentiation attempt, but it is unverifiable against the sibling list and conflicts with the existence of rm_gates_run. The stage explanation is parameter semantics, not tool-selection guidance.

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