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

Annotations already declare readOnlyHint=true, destructiveHint=false, so the safety profile is covered. The description nonetheless adds substantial behavioral context: filters are ANDed, default sort is cheapest first, prices are unconverted (mixed currencies when mixing countries), null-priced items are excluded from sorts/stats, data freshness (fetchedAt Jun–Sep 2026), and coverage counts. This goes well beyond the annotations.

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?

Long but well-structured with a dedicated 'How to target a place' list and a returns line. Nearly every sentence carries actionable detail, though the coverage statistics are somewhat tangential to invoking the tool.

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?

There is no output schema, and the description supplies the return shape ({ data, total, page, limit, stats? }), the stats semantics (min/avg/max when country is set), and the per-item fields (category, restaurant). An agent has everything needed to call and interpret the result.

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 only 47% across 15 params, so the description must compensate and largely does: it explains the non-obvious semantics of city/area/postcode, plus the weak-reliability caveat for vegetarian/alcohol. It leaves some params (restaurantId, discounted, priceMin/priceMax, explicit sortBy/sortOrder) to the schema, which is a minor gap.

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 ('Search GrabFood menu items (dishes, drinks) across restaurants'), adds a concrete use case, and is clearly distinguishable from Grab_search_restaurants and Grab_get_restaurant.

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?

Explicit routing guidance: when to use city vs area vs postcode, the pitfalls of each ('Kemang' also matches 'Kemanggisan'), and a pointer to Grab_list_areas for the city list. It also warns when dietary flags should be distrusted and suggests name searching as an alternative.

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