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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds beyond that: clamping behavior, row limits, per-row error isolation, and the '0 removes' semantics. It also notes that printId defaults to the standard released printing, which is non-obvious. This provides actionable detail without contradicting the annotations.

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?

The description is a single paragraph with multiple sentences, but each sentence adds a distinct piece of information: mode behavior, clamping, row limit, error isolation, and printId default. It is front-loaded with the main purpose and avoids fluff, though the density could be slightly streamlined. Still, it earns its length.

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 destructiveHint=true and no output schema, the description covers all critical calling constraints: how to specify changes, limits, error handling, and defaults. It also hints at the response format ('each row reports before/after'), giving the agent a clear picture of what to expect. Nothing essential is missing for a correct call.

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 0%—only cardNumber has a description. The description explains the meaning of 'mode' ('add' vs 'set'), the effect of count (including 0 removal and clamping), the role of printId, and the row limit. It fully compensates for the missing schema descriptions, making parameters self-explanatory.

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 clearly states the verb 'Change' and the resource 'owned counts in the signed-in user's collection', distinguishing it from read-only siblings like my_collection. It also specifies the two modes ('add' and 'set') and the effect of 'set' with 0, which uniquely identifies this as the update tool.

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 description provides explicit behavioral context: mode semantics, count clamping (0–99), row limit (up to 20), partial failure (a bad row doesn't block others), and the default for printId. While it doesn't name alternative tools for when not to use it, the context is specific enough that an agent can infer when to call this tool for collection updates.

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