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

Annotations already establish the safe read-only, idempotent, closed-inventory profile, so the description's job is supplementary; it does add real scope information ('independent UK restaurants that use TableSpark') and signals the return payload contains a restaurant_id. It does not mention result capping or pagination behaviour, which is the main undisclosed trait for a search tool that defaults to 8 and caps at 20.

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 short sentences, front-loaded with the core purpose and the workflow instruction before the optional filters. Every sentence carries distinct information and nothing is repeated verbatim from the schema.

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 zero-required-parameter, read-only search over six parameters, the definition covers purpose, filter behaviour and the follow-up step that consumes its output. The only meaningful omission is result-size/pagination behaviour, which matters given the limit default of 8 and maximum of 20.

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 83%, so the schema already explains town/postcode forms, free-text query, cuisine, offers and open_now. The description restates these at a high level (name, dish, cuisine words, town or postcode) without adding syntax or matching-behaviour detail such as how multiple free-text words are combined. With the schema doing the heavy lifting, baseline 3 applies.

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 gives a specific verb and resource ('Find independent UK restaurants that use TableSpark') plus the searchable fields (name, dish, cuisine words, town, postcode), and scopes it to a single provider's inventory. It also states the tool's role in the workflow ('Use this first to get a restaurant_id'), which separates it from siblings like get_restaurant without needing to open their schemas.

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?

There is explicit sequencing guidance: use this first to obtain a restaurant_id, implying detail/link tools come afterwards. The optional filters (open now, table bookings, online orders) are framed as narrowing conditions. It stops short of naming an alternative for direct ID lookup or saying when not to use this search, so it is clear context rather than full when/when-not coverage.

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