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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description goes further by disclosing the full analysis surface (missing required parts per task kind, specific risk categories like irreversible steps without a stop rule, secrets, vague goals, multiple jobs) and the three-part output. It stops short of noting things like latency or whether `repo` facts change scoring, but adds substantial context beyond 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?

It is front-loaded with the trigger and closes with the returns, so nothing is buried. The middle is one long parenthetical enumeration of ten required parts and four risk classes, which is informative for capability discovery but dense and hard to scan; a short list would read faster without losing content.

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?

An output schema exists, yet the description still names the three returned artifacts, and it fully describes the checks performed and the risk categories. For a three-parameter, read-only analysis tool this leaves nothing an agent needs to decide to call it or to interpret the trigger correctly.

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 67%, so the schema already explains `repo` (optional standing facts) and `brief`, and the enum on `agent` is self-describing. The description adds no parameter-level guidance—nothing on how `agent` selection changes which parts are required, or what belongs in `repo` versus `brief`—so it only matches, not exceeds, the schema baseline.

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 ('check the brief') plus the exact trigger moment ('Before a task goes to a coding agent'), and enumerates what gets examined: task type, required parts missing, and risk patterns. It also names the concrete return artifacts (readiness out of 10, rewritten brief, starter CLAUDE.md/AGENTS.md), so an agent can tell this is a brief-linting tool, distinct from lint_prompts or check_answer.

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?

'Before a task goes to a coding agent' gives an explicit, actionable timing cue rather than a vague purpose. There is no explicit when-not-to-use clause and no named alternative (e.g., lint_prompts for prompt text vs. a task brief), but no sibling tool actually overlaps, so the missing exclusion is low-cost.

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