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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety bar is low, yet the description adds substantive behavior: pricing is resolved per-item at the needed amount, unpriced items are excluded from totals, stops are capped by maxStores and filtered by preferBanners, and price.how/approximate explain non-comparable sizes. The only notable omission is whether list state changes as a side effect of the pricing decisions surfaced in stops.

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?

It is front-loaded with what the tool returns and stays dense but purposeful, with each clause covering a distinct output concept (pricing, stops, meals, totals, id routing). The nested phrasing ('its own amount plus its meals'') and backtick-heavy field references make it slower to parse than it needs to be, but there is no filler.

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?

With no output schema and a fairly complex return shape, the description carries the burden well by explaining price.how, approximate, stops grouping, per-meal cost share, mealIds linkage, and the totals exclusion rule. Given all four parameters are fully documented in the schema, what remains missing is minor, chiefly the ordering or pagination of items and meals.

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 description coverage is 100% and the schema itself explains near/radiusKm persistence, maxStores splitting logic and null-clearing, and preferBanners examples, so the heavy lifting is already done. The description restates maxStores/preferBanners effects on the stop grouping rather than adding new parameter meaning, which is the baseline case rather than an enhancement.

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 identifies a specific resource ('the user's grocery list and the meals behind it') and scopes it as a shared, synced read of Gaurmon-maintained state, which is clearly distinguishable from mutating siblings like update_list and update_meals. It never uses an explicit retrieval verb, opening with a noun phrase instead, but the resource and its boundaries are unambiguous.

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?

It routes the agent for mutations ('Ids are for update_list and update_meals') and hands the decision about which stores to visit back to the caller ('Which stores to visit, and when, is yours to suggest'), which is useful framing. However, it gives no explicit when-to-use guidance against read siblings such as get_savings, compare_items, coverage, or price_history, so an agent must infer the boundary.

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