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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered structurally. The description adds the lint scope (tags, assets, layout) and points to get_skill('verify'), but says nothing about output format, blocking behavior, or failure reporting.

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 terse fragments that front-load the purpose before the pairing hint. Nothing is wasted, though the fragmentary style ('see get_skill(verify)') is slightly cryptic.

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 read-only lint tool with full schema coverage and annotations, the description covers purpose and pairing. It does not indicate what the lint returns or how failures surface, though the get_skill('verify') referral partially compensates and there is no output schema to imply structure.

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 coverage is 100%, so all four parameters (including the notable 'context' logging constraint and guestToken flow) are already documented in the schema. The description adds no parameter-level detail, so it lands at the 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 operation (pre-publish lint) and enumerates what it checks (tags, assets, layout), which lets an agent distinguish it from siblings like preview_page. It never says 'page' explicitly, relying on the tool name, but the intent is unambiguous.

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?

The phrase 'Pre-publish' sets a clear triggering context, and 'Pair with preview_page' names the related sibling it is meant to accompany. No explicit when-not condition is given, but the pairing guidance is actionable.

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