Delimit Handoff Preflight

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

The description itself is exemplary — 'READ-ONLY', 'NO writes, env mutation, git config changes, network, ledger, or notification', fail-closed verdict semantics, and an explicit phase-1 not-wired-into-live-path disclosure. However, the annotations declare readOnlyHint=false, which directly contradicts the description's emphatic read-only/no-writes claims; per rubric, a description that contradicts its annotations scores 1. Annotation Contradiction.

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?

Long but front-loaded: the first sentence states the purpose, and each paragraph carries distinct information — when/when-not, sibling contrast, phase limitation, side effects, and verdict semantics. No filler or repetition; the LED-1710 reference is the only minor noise.

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 single-parameter tool that already has an output schema and annotations, the description covers selection (when/not-to-use), invocation safety (read-only, hermetic git env), result interpretation (fail-closed, critical vs warn severities, per-check record shape), and operational limitations (phase-1 validator only). Nothing needed for correct selection or invocation 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 description coverage is 100% — project_path is fully documented as 'Repository path to inspect. Empty resolves via the gateway resolver, then cwd.' The description adds tool-behavior context (which state is inspected at that path) but no new parameter-level semantics, so the high-coverage baseline of 3 holds.

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?

Opens with a specific verb+resource pair: 'Validate cross-agent handoff invariants before switching coding agents.' It names the exact invariants checked (core.bare=true, git identity, GIT_* env leaks, index.lock, .last_capture) and explicitly differentiates itself from delimit_revive, delimit_soul_capture, delimit_repo_diagnose, and delimit_gov_health, so an agent can select it from ~200 siblings without opening any schema.

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?

Provides explicit when-to-use ('before a session hands off to a different coding agent... or an Auto-Phoenix revive'), when-not-to-use ('to capture or restore session context... or for general repo health'), and names the exact alternatives (delimit_soul_capture, delimit_revive, delimit_repo_diagnose). The sibling contrast adds exclusion criteria by noting delimit_revive is read+write while this is a narrow read-only gate.

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