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

With no annotations, the description carries the full burden and delivers little: no mention of ordering of results, pagination via the limit cap, whether deleted or newly-created businesses appear in the feed, or whether results are bounded by a time window. 'Freshness feed' hints at recency ordering but doesn't commit to it.

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?

Two short, front-loaded statements with no filler; the core concept (changed since) leads. The opening noun-phrase fragment rather than a verb statement is a minor stylistic weakness.

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 two-parameter read tool with no output schema this covers the essential concept, but leaves the agent guessing about limit behavior, result ordering, and whether deletions are represented — questions an agent must answer to poll correctly.

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 50%: 'since' is documented (ISO 8601 with example), but 'limit' has no description in either schema or prose. The description's 'since a given moment' merely restates the documented parameter and offers nothing on limit, pagination, or cursor advancement.

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?

Names a specific resource (businesses) plus the discriminating filter (changed since a given moment) and characterizes the result as a 'freshness feed.' This is enough to tell it apart from get_business and search_businesses even though neither sibling is named.

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 it to stay in sync without re-crawling' gives one motivating use case and implicitly contrasts with repeated search_businesses calls. It stops short of explicit when-to-use vs. when-not, and never names an alternative tool or states prerequisites.

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