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

Annotations only declare the safety profile (non-read-only, non-destructive, closed-world); the description adds genuinely new behavior: the write is an upsert merged on the composite key card+version+language+condition, quantity is capped at 20, and the call requires the mcp:collection:write scope. It does not say what happens when a grader/gradeLabel combination conflicts with the base-stack key, which is the main remaining gap.

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?

Four short sentences, each carrying distinct information (scope, merge semantics, limits, auth, prerequisite), with the most decision-relevant fact front-loaded. No filler or restatement of the title.

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 9-parameter mutation with no output schema, the description covers the essentials an agent needs to invoke it safely: write scope, upsert behavior, quantity bound, and how to obtain cardId. It could go one step further on graded-card field interactions and on what the upsert returns, but nothing critical to a correct call 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 only 33%, so the description has to carry weight; it does explain the upsert identity key (card+version+language+condition) and the 1-20 quantity bound, and it points cardId sourcing at lookup_card. However, grader vs gradeValue interplay, language formatting, and purchasePriceEur are left entirely to an undocumented schema. Baseline 3 for partial compensation.

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?

"Add ONE card to the binder" gives a specific verb plus resource with an explicit single-item scope, which implicitly separates it from add_sealed (sealed product) and from any bulk operation. The capitalization of ONE reinforces unit semantics. It stops short of naming a sibling to contrast with, so it lands just under a 5.

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?

It supplies a concrete prerequisite and routing instruction: "Use lookup_card to get cardId", which is exactly the kind of when-to-use linkage an agent needs. It does not state exclusions (e.g. use add_sealed for sealed product, or update_copy to change an existing copy's fields), so an agent must infer the boundaries.

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