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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds substantial behavior beyond that: the three hosting modes and their branching, the side effect of creating a brand-new rikma when newRikmaName is supplied, the membership requirement, and what the call returns (new Matanot id and where it lives). It does not discuss validation failure behavior or partial-failure on the newRikmaName path, which keeps it from a 5.

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?

Front-loaded with the three hosting modes, then the storefront field list, then the alternative-tool routing, then return value and docs link — a sensible hierarchy. It is dense but not padded; the only slight waste is re-listing schema fields (name, description, price, stock) that the schema already documents.

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 14-parameter mutation tool with nested objects and no output schema, the description covers the hosting-mode decision tree, permissions, the state-changing side effect of rikma creation, and the return value. An agent has enough to invoke it correctly on the first attempt.

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 adds cross-parameter meaning the schema cannot express: projectId alone vs omitted vs newRikmaName are mutually exclusive hosting modes with different ownership outcomes, which is the single most error-prone decision in this call. It also clarifies quant=-1 as unlimited and the quant×price interpretation behind kindOf.

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?

States a specific verb and resource — 'Create a fixed-price product (Matanot) for the rikma' — and immediately differentiates itself from the sibling createComplexMatanot (complex recipe/BOM) and implicitly from createRikmaProductsBatchTool. An agent knows exactly what this produces without consulting any other 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?

Gives explicit routing: use this for the simple shippable shelf item, use createComplexMatanot for BOM/margin/estimated-price recipes. It also names the prerequisite helper tools (listRikmaCategories, upsertProductVariants) and the permission condition ('Members or personal owner'), leaving little to inference.

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