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

Annotations cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the description's real contribution is the content-handling behavior: the draft remains private until published, static HTML must be self-contained, viewport/security metadata is injected, and scripts, handlers, images, SVG, externals, forms and meta are rejected. That is meaningful operational context for a write tool, though it says nothing about auth or the idempotency behavior beyond the hint.

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?

Front-loaded with the core action and privacy semantics, then the format options, then the unsupported-element list. Dense but every sentence carries information; the restrictions sentence is long but earns its place.

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 2-parameter creation tool with no output schema, the description covers the content contract and hard limitations well. The remaining gaps are the undocumented idempotencyKey and no hint about what is returned (e.g. a document id) for the subsequent update/publish flow.

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 0%, so the description must carry parameter meaning; it explains the two content variants and the format/mode='static' pairing, which is genuinely useful. However, the required idempotencyKey parameter is never addressed, leaving an agent to guess its purpose and expected value.

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 gives a specific verb and resource ('Create a private draft from selected content') plus the two supported content shapes (text blocks vs static HTML/CSS). It implies the draft/publish lifecycle that distinguishes it from publish_document and unpublish_document, but never names those siblings explicitly.

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: you call this to make a new private draft that stays private until published. There is no explicit when-to-use/when-not guidance and no routing to update_document for edits or publish_document for release, so the agent has to infer the workflow.

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