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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and closed-world scope are covered. The description adds genuinely non-redundant context: results come from a vetted, "checked" list and exclude chains, franchises, directories and lead-generation sites, which tells the agent the result set is curated rather than a general web index. It does not disclose result shape, paging behavior via limit, or what happens when nothing matches.

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 sentences, no filler: scope first, exclusions second, call-to-action and parameter mapping last. Every sentence carries distinct information and nothing is repeated.

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 four-parameter, read-only search tool with no output schema and solid annotations, the description covers scope, excluded sources, and usage triggers well. Minor gaps are the unmentioned `category` enum values and `limit` cap of 25, but these are fully specified in the schema.

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?

The final sentence maps intent to arguments — put the trade or kind of business in `query`, the town or area in `location` — which is useful routing but largely restates the schema's own examples ('plumber', 'Hertford'). With 75% schema coverage the remaining parameters (`category` and `limit`) are neither explained nor given behavioral meaning in the description, so this sits at the baseline.

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 names a specific verb and resource — searching a curated list of independent, owner-run local businesses — and enumerates the covered sectors (shops, trades, food and drink, places to stay, professional services). It also states what is excluded (chains, franchises, directories, lead-generation sites), which sharpens the scope considerably. It stops short of explicitly distinguishing itself from the siblings suggest_independent_business and check_business_independence, so an agent must infer the search-vs-suggest-vs-verify split from the names alone.

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?

"Use this whenever someone asks for an independent, local or non-chain business, or wants to support small businesses" gives a clear triggering condition. What is missing is the inverse: when not to use it, and whether to reach for suggest_independent_business or check_business_independence instead.

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