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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description reinforces idempotency ('repeat calls change nothing and honestly answer changed=false') and adds valuable context: empty change list is a valid response, the tool publishes nothing, and it discloses the excluded work domains. It adds meaningful behavioral context beyond the annotations without contradicting them.

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?

The description is structured with clear sections (verdict, safety note, idempotency, exclusions, measurement protocol). It front-loads the core function in the first sentence. It is somewhat verbose and uses heavy formatting (⚠️, ALL-CAPS emphasis) which carries important warnings but could be trimmed. Every sentence serves a purpose — no filler.

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 transformation tool with two well-documented parameters, a good safety model (non-publishing), output schema present, and idempotency annotations, the description is thorough: it covers return semantics (changed=false), the workflow contract (human approval before publish), exclusion boundaries (site_issues), and measurement guidance (check_performance threshold). Given the annotations and schema richness, this is complete.

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% with both parameters documented. The description's main added value is the global scope note (tool is non-publishing, idempotent) rather than per-parameter detail. The fix enum values are well described in the schema; the description reinforces contextually. Slight deduction since the description doesn't add per-parameter meaning beyond the schema, though the fix semantics are already rich there.

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?

The description states a specific verb+resource: 'apply one named transformation to markup with a predictable result.' It clearly distinguishes from siblings by explicitly stating it returns modified HTML rather than publishing, naming publish_landing as the separate publishing step. The distinction from site_issues (which reports problems it doesn't fix) is explicit.

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?

One transformation (rendering) produces HTML instead of publishing; the description explicitly tells the agent to show it to a human, get consent, and call publish_landing. It clearly states when NOT to use it: fonts from third-party hosts, webp conversion, and inline-style parsing are excluded and belong to site_issues. It also specifies when to use it — measuring wins via check_performance before/after, with noise threshold of three points.

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