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

Annotations already establish read-only, non-destructive, open-world behavior. The description adds real value beyond that: the two mutually exclusive paging strategies, the requirement to keep filters constant across pages, the loop-until-hasNextPage stop condition, and the fact that notRecommended reviews omit photos/videos/reactions.

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?

Purpose and pagination are front-loaded before the long return-value enumeration. The inventory of review fields is lengthy, but it earns its place since no output schema exists to document the payload.

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 fully covers the return shape (author profile, text, rating, photos, reactions, tags, owner reply, business rating/language totals) and the pagination contract. Combined with 100% schema coverage, an agent has everything needed to call and page 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 description coverage is 100%, so the schema already documents every parameter, including the start/num/nextPageToken interaction. The description's paging walkthrough (step start by num, or resend nextPageToken) synthesizes the schema but adds little that isn't already there, matching the baseline 3.

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 ('Fetches the review feed of a single Yelp business by Yelp ID') with scope, and the Yelp branding plus 'single business by Yelp ID' clearly distinguishes it from the Amazon/Google Maps/Walmart review siblings.

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?

Gives explicit pagination procedure and concrete use cases (sentiment monitoring, competitor complaint mining, response tracking, rating-distribution datasets). It does not name the sibling that supplies the placeId (yelp_search_getSearchResults) nor state when to prefer it over other review sources, so it stops short of 5.

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