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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, yet the description adds substantial context beyond them: the text is never executed, links never fetched, referenced files never read, results are deterministic with no LLM, and there are explicit size limits (300 KB text, 512 KB request). It also discloses that credentials are reported by pattern name and line and never echoed, and that matches in negated or quoted sentences are downgraded to warnings — real behavioral detail an agent cannot get from the annotations.

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?

Purpose is front-loaded, which is good, but the body collapses into a very long semicolon-chained enumeration of every rule checked. The content is dense and largely earns its place, yet the wall-of-text form makes it hard to scan and mixes purpose, rule catalog, and safety guarantees into one block.

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 carry the burden of what the tool does and returns; it thoroughly enumerates the checks (frontmatter fields, body length, paths, hidden characters, credentials, unsafe instructions) and hints at severity via warnings vs. flags. What it omits is the shape of the result — finding fields, severities, counts, overall pass/fail — which an agent needs to consume the output.

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 all three parameters are already documented in the schema (including the `kind` enum semantics and the files-only-names comparison). The description reinforces some of this ('referenced files missing from an optional sibling file list'), but adds no new syntax or format information beyond what the schema provides, so the baseline 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?

Opens with a specific verb+resource: 'Static lint of an agent instruction file', then names the exact artifact types (Agent Skills SKILL.md with YAML frontmatter and markdown body, or AGENTS.md / CLAUDE.md). This resource scope cleanly separates it from siblings like mcp_tool_lint and agent_card_lint without needing to name them.

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 by the resource it targets rather than stated as when/when-not guidance; there is no explicit routing against alternatives such as mcp_tool_lint or agent_card_lint. The only conditional guidance is for the optional `files` parameter ('Omit to skip the missing-file check'). Adequate but leaves the agent to infer selection.

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