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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) by disclosing that the link is public, that the document is not attached to any record, that complete HTML is used as-is with no letterhead, and that <script> is disallowed. It also prescribes an inspect-the-preview step before telling the user it's ready.

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, mentions the sibling, then details modes and caveats in a logical order. Dense but every sentence carries operational content; the parenthetical examples are slightly loose but not wasteful.

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?

Covers inputs, the public-link caveat, the absence of record attachment, and even the return shape (link, summary, page-1 image) despite no output schema. Nothing essential for correct invocation is missing.

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 the baseline is 3, but the description adds real meaning: the two-mode contract of `html` (body gets branded letterhead vs. complete document used as-is) and how evidence of rendering is returned. It doesn't expand on brand/filename beyond the schema.

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+resource ('Turn a report or document you write as HTML into a PDF and get a link') and explicitly resolves identity ambiguity against the copilot's own generate_pdf. An agent can tell this apart from generate_document/generate_estimate siblings via the HTML-to-PDF framing.

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?

Gives clear triggering context ('when the workspace's instructions or an action's answer say to call generate_pdf, this is it') and routes attachment to the workspace's own action or propose_write. It does not explicitly contrast with generate_document, so it stops short of a full when/when-not.

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