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

Annotations confirm this is a non-read-only, non-destructive, closed-world write, so the safety bar is already partly covered. The description adds genuinely new behavioral information: duplicate itemIds merge into an existing 'family row' and increment rather than duplicating, and free plans cap at 10 distinct products. It stops short of saying whether the limit raises an error or silently refuses, and omits default quantity.

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?

Three short sentences, with the core action front-loaded and zero filler. The final fragment 'Free plan: 10 distinct products' is telegraphic — it states the cap without the consequence — which costs a point against an otherwise tight structure.

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 three-parameter mutation with no output schema and no annotation coverage of merge semantics, the description covers the merge and plan-limit behaviour but leaves parameter meaning and failure modes undocumented. An agent can call it, but cannot confidently predict what purchasePriceEur does or what a limit breach returns.

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% for all three parameters, so the description must carry the burden. 'Same product' hints that itemId is a product identity key and 'increments' hints at quantity, but purchasePriceEur is never mentioned and no format, default, or unit details are given. The schema's bare types leave real ambiguity that the description only partially resolves.

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?

Opens with a specific verb+resource ('Add a sealed product'), and the word 'sealed' naturally separates it from the sibling add_card. The second sentence clarifies that re-adding the same product does not create a new row, which sharpens what the tool actually does. It falls short of 5 only because it never names a counter-tool (e.g. add_card, update_sealed) 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?

There is no explicit when-to-use/when-not guidance or routing to alternatives such as add_card versus add_sealed or update_sealed. The only guidance-like content is the constraint 'Free plan: 10 distinct products', which tells the agent a ceiling exists but not what happens at it or how to check remaining capacity. Usage is therefore implied rather than instructed.

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