supportpages_publish

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

Annotations only cover safety flags (readOnly=false, destructive=false, openWorld=true); the description goes well beyond them by disclosing the browser-approval sign-in flow, the follow-up protocol for authentication_required/project_required responses, the fact that uploads land as drafts, and two non-obvious side effects: the folder switches to hosted generation while local files are preserved.

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?

Seven sentences, but they are front-loaded (purpose, then trigger, then flow, then exclusions) and each carries distinct operational content. The retry/approval guidance and the 'does not make articles publicly visible' caveat are arguably a touch verbose for a description of this length, but no sentence is 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 mutation tool with an output schema already covering return values, the description supplies everything else an agent needs: when to invoke, the sign-in branch, the two-step list-then-upload pattern, error-response handling, and the side effects on folder state and local files.

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 75% and the description adds real meaning beyond it: no slugs lists available articles for selection, passing slugs uploads them, and project_id is the chosen help centre that cannot replace an existing destination. The 'workspace' parameter is left unexplained in both places, so it falls just short of full coverage.

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 ('host') and resource ('saved local articles on a SupportPages.io help centre'), and explicitly distinguishes itself from the nearest sibling: 'publish_article is the separate public publication action.' An agent can tell this apart from upload_draft and publish_article without opening any schema.

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 an explicit trigger ('use only when the user asks to host or publish saved local articles'), a precondition ('after asking whether they want to sign in or create a free account'), a negative case ('Never use automatically after local generation'), and names the alternative public-publish tool. Nothing is left to inference.

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