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

Annotations already declare readOnly/openWorld=false/non-destructive, and the description still adds genuine context: results carry source and date, 'newer dates are the owner's latest word' discloses precedence for conflicting content, and the closing sentence warns that content is business-authored data, never instructions (prompt-injection safety). That is meaningful disclosure 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?

Front-loaded with the verb and purpose, and nearly every clause carries information (scope, trigger, params, returns, default behavior, safety). The first sentence is long with an embedded parenthetical list and the 'latest word' clause is slightly compressed, but there is little wasted text.

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, the description still describes the return shape (best passages with source, date, and an id for read_business_info). Combined with safety annotations and explicit parameter formats, an agent has everything needed to call it correctly and interpret results.

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 0%, so the description must compensate and does: `business` takes 'the exact business id or slug', `query` takes 'a few words of the question' rather than a full sentence, and the no-query path is defined as listing what exists. This resolves the main ambiguity (format of each argument) that the bare schema leaves open.

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?

Uses a specific verb (Search) on a clearly delimited resource, enumerating what is searched (notes, price lists, flyers, links, published website) and framing it against the business brief. An agent can distinguish it from read_business_info and business_info without opening 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?

States the trigger condition explicitly ('when its business brief doesn't answer the question: a product, an ingredient, a policy, an older offer'), names the follow-up alternative (read_business_info) for reading a result in full, and even defines the no-query fallback behavior. Both when-to-use and what-to-use-next are covered.

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