worktree_audit

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

readOnlyHint=true already establishes the safety profile, so 'Never deletes anything' largely restates the annotation. The description does add real context beyond the annotation by disclosing what the audit produces (safety verdicts, recommendation items) and that duplication detection covers build caches, but says nothing about performance cost or scope limits.

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?

Three short sentences, zero filler, and the most important fact (read-only, scoped audit) is front-loaded. Nothing repeats the tool name or wastes tokens.

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 no output schema, the description must convey the return shape, and it does at a high level (safety verdicts, recommendation items). All parameters are optional so there is little invocation risk, but the description could say more about what a verdict item looks like or how many worktrees are covered.

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 four parameters (json, sizes, worktree, workspace_path) including the default-all behavior and the slower sizes option. The description adds no parameter-level detail, which is the expected baseline when the schema does the work.

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: a read-only audit of git worktrees plus build-cache duplication, scoped to 'this repo'. This clearly separates it from siblings like worktree_status and worktree_gc, though it never names those alternatives explicitly.

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?

Usage is implied ('audit ... reports safety verdicts and recommendation items') but there is no explicit when-to-use versus when-to-use-something-else guidance, no mention of running it before worktree_gc or how it relates to hygiene_report. The agent must infer the pre-cleanup context.

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