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

Beyond the readOnly/idempotent annotations, the description discloses data provenance (Google Maps listings), that figures are sample-based rather than exhaustive ('how many listings the sample holds'), masking of phone numbers, and a hard cap of 10 example records. These are the operational details an agent needs to interpret and present results honestly.

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?

One long but dense sentence delivers the return contents, followed by a short coverage sentence and a fallback clause. Lead information (what the snapshot is) comes first, 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?

With no output schema and no annotations covering semantics, the description carries the burden of explaining return values and does so field by field, plus coverage limits and fallback behavior. An agent can decide whether to call it and how to present the result without further information.

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 100%, so a baseline of 3 applies; the description adds the constraint that both business_type and city describe exactly one type in one locality, reinforcing that this is a single-pair query. The country list mirrors the schema's enum-like description, so it adds no new information but the single-pair framing does.

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 resource (a snapshot of one business type in one city) and enumerates exactly what the snapshot contains: listing count, average rating, typical review count, website/phone coverage shares, and up to 10 examples. An agent can tell this returns an aggregate market profile rather than a raw listing set, which separates it from a filtered-list sibling like find_businesses_without_website.

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?

Geographic coverage is stated explicitly and the fallback ('when a city or business type is not covered, the result lists what is') implies calling list_available_markets, but that sibling is never named and no when-not-to-use condition is given. Usage is inferable rather than directed.

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