Ready-to-post content kit

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

Adds substantial behavior beyond the annotations: "Nothing is posted automatically", a review page the seller edits before sharing, hosting lifetime differences (Free: 7 days with a small mark; Pro: 90 days, no mark, own logo and colours), and a distinct local mode that writes an HTML file instead of hosting. These clarify real side effects and state transitions that readOnlyHint=false/openWorldHint=true do not convey. It does not cover cost, rate limits, or what happens to an existing kit when kitId is reused, so a 5 is not warranted.

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 purpose and output formats, then organized into hosting-mode and image-guidance blocks that scan well. A few sentences are dense parenthetical run-ons (the Share/phone-share-sheet sentence in particular), but no sentence is purely 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 25-parameter tool with nested objects and no output schema, the description covers the pipeline end to end: what is produced, where it lives, how the seller reviews and shares it, and what happens in local versus connected mode. The remaining gap is parameter-level detail across theme, niche, and timeZone, which the 68% schema coverage mostly absorbs.

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?

At 68% schema description coverage the schema carries most of the load, and the description does add meaning for a few high-risk inputs: which image source applies (products[].image or images), that brandStyle "always wins over the event theme", and that price and deadline should be omitted rather than fabricated. Many of the 25 parameters (niche, timeZone, theme, displayName nuances) get no coverage in the description at all, so it partially compensates rather than fully.

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 and resource ("Make finished social graphics with captions for a sale or launch") and enumerates the exact deliverables and aspect ratios (offer post 4:5, spotlights 1:1, carousel, Story 9:16, X/LinkedIn 16:9), which clearly separates it from planning siblings like content_plan and page siblings like landing_page. It stops short of naming the sibling it is not, so an agent must infer the boundary from the output format rather than being told 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?

Gives real conditional guidance inside the task, notably the image policy ("the seller's own photos are best... If you can generate images yourself, generate them... Otherwise free licensed photos are found automatically") and the constraint "Never invent prices or deadlines; leave them out if unknown." However there is no explicit when-to-use versus alternatives statement, and no mention of whether content_plan should run first or how this relates to publish_page beyond consuming its link.

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