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

Annotations only declare readOnlyHint=true; the description adds far more — that results come from the shelf snapshot at plan-build time rather than a fresh search, that a plan older than ~15 minutes has expired, and that calling it does not mutate the shopper's list. That is genuine behavioral context beyond the annotation. It stops short of describing the shape of what comes back, which is the one trait left undisclosed.

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 paragraphs, each doing distinct work, with the core action and precondition front-loaded. Minor slack in phrases like 'the rest have nothing else to show', but no sentence is genuinely wasted.

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 3-parameter read-only tool with no output schema, the description covers provenance, expiry, and the non-mutating guarantee well. The remaining hole is that an agent is never told what the response contains (product entries, pricing, availability), which matters more since there is no output schema to fall back on.

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 provenance the schema lacks: jobId 'from build_plan' and 'the item' tied to the qualifying condition (otherOptions above 0). Those constraints on which identifier to pass are not derivable from the schema alone. The storeId default is already documented in the schema, so nothing more was needed there.

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 with explicit scope: 'Show the other products available for ONE item at ONE store, from a plan you already built.' The capitalized ONE item/ONE store narrows it in a way no sibling (find_nearby_stores, refine_items, build_plan) duplicates, so an agent can route to it without opening a 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 both triggering conditions ('when a pick from build_plan is not what the shopper wanted, or when they ask what else is available') and a hard negative precondition ('Only offer this for items whose pick reported otherOptions above 0'). It also closes the loop on the follow-up action by naming LastList as the place a choice is recorded, which rules out the wrong next step.

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