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

Goes well beyond the annotations by disclosing partial-failure semantics ("Every item is answered on its own (results[i]); one failing item never stops the others") — a property no annotation conveys and which directly affects how an agent should read the response. It also explains the per-product proposal model (own clock and vote), the immediate-apply exception for personal products, and the membership requirement. idempotentHint=false is consistent with the described propose-per-product behavior.

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 front-loaded sentences that earn their place, with the cap, rikma scoping, and per-item isolation stated first. The parenthetical about editObject ("one decision per object, with its own clock and vote") is slightly jargon-heavy and could be tightened, but it carries real domain meaning.

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 batch mutation tool with nested items and no output schema, the definition covers the essentials an agent needs: the 50-item cap, the single-rikma constraint, membership, per-item results, and independence of failures. What is missing is minor — it does not preview what a returned proposal contains or how to confirm the outcome after the 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?

With only 50% schema description coverage, the description does add useful meaning: it clarifies that items is a list of per-product edits, capped at 50, all bound to a single rikma, and that each entry produces its own proposal. It does not explain the individual edit fields (name, price, reason, categories, pricingMode) or their differential behavior, leaving that half of the semantics to the schema, so a baseline 3 is appropriate.

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 ("proposeProductEdit for up to 50 products of one rikma in one call"), which both identifies the operation and implicitly distinguishes it from the single-item sibling proposeProductEditTool. The batch scope and the one-rikma binding are stated up front, so an agent can tell it apart from createRikmaProductsBatchTool or updateRikmaProductTool without opening any schema.

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 a clear operating context: "one rikma", max 50 products, and the constraint "Members only", plus the crucial domain rule that a proposal belongs to one product, so each product gets its own proposal. It does not explicitly say "use proposeProductEditTool instead for a single product" or state when-not to use this tool, which keeps it below a 5.

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