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

Annotations carry only false hints and no real behavioral signal, so the description must carry the burden. It does disclose the key non-obvious behavior that 'a repriced line keeps its old rows' and states the 25-SKU free limit. It does not mention auth or response shape, but neither is essential for invoking a write operation.

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 sentences with no filler: the first states purpose and key fields, the second adds the crucial versioning side effect, and the third gives the quota. Everything earns its place and the most important information is front-loaded.

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 10-parameter tool with no output schema and weak annotations, the description covers the purpose, pricing dimensions, history behavior, and a usage limit. The schema documents the remaining parameter details. A small gap is the lack of any note about return values, but that is not required given the schema already documents fields.

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 90%, but the description adds the compound-key nuance that price_minor is set 'for one currency, tier and valid_from'. This is real meaning beyond individual schema field descriptions, clarifying how the SKU's price matrix is structured.

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 opens with a specific action and resource: 'Add a catalogue line or reprice one'. It also names the core inputs, making it unambiguous that this tool creates or updates SKU pricing, distinct from siblings like sku_get, sku_list, or sku_delete.

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 implies the tool is for adding or repricing catalogue lines, and the free-tier note gives a constraint, but it never explicitly says when to prefer sku_set over a sibling or when not to use it. The 'keeps its old rows' fact is behavioral, not an exclusion or alternative.

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