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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral detail beyond that: the image is 'the same card the site's share button makes', the short link 'counts the click and sends the reader straight to the store's page', and style 'f' only renders when there is a saving. The undefined gap is how the PNG is delivered (returned buffer, URL, or attachment).

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?

Every element mentioned is substantive, but it is delivered as one long comma-spliced sentence with nested parentheticals listing formats and designs, which forces re-reading to separate the returns from the options. Front-loading is present ('One promotion ready to publish elsewhere') but the structure hurts scanability.

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?

With no output schema, the description carries the burden of explaining the return, and it does so thoroughly: image variants, designs, short link behavior, store page, and caption. The one significant omission is whether the card image is returned inline, as a base64 payload, or as a fetchable URL - an agent needs that to actually use the result.

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 goes past the enum labels: it names each design in human terms ('Vandaag €x goedkoper' with the price large), maps each size to its channel (feed, story, link preview), and adds a constraint absent from the schema - style f requires a saving - plus the fact that the default style comes from the promotion itself.

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 conveys a specific resource (a shareable promotion card) and enumerates exactly what comes back: a PNG in several formats, a click-counting short link, the store page, and a caption. It is not phrased as a verb+object purpose statement, and it never explicitly contrasts itself with siblings like get_deal, but an agent can tell from the output inventory what the tool is for.

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?

The closing line 'Use the id from search_deals or get_deal' gives a clear prerequisite and points to the right upstream tools. It says nothing about when not to use it - e.g. whether to call this versus just fetching deal data, or whether repeated calls are expected - so usage is implied rather than fully specified.

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