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

Annotations already declare non-read-only, open-world, non-idempotent, non-destructive behavior, and the description adds genuinely new context beyond that: latency expectations (~1 minute for 60), side effects (results persisted in the user's Puley history with a spreadsheet download link), and provenance (contact details are each business's own published ones). It does not cover failure modes or what happens with zero results, but the added context is meaningful.

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?

The opening sentence is long and clause-heavy, cramming the return shape, provenance, and table format into one breath before the parameters are addressed. Later sentences become telegraphic fragments ('what: the kind of business', 'count: up to 60 a call'), which are efficient but inconsistent in register with the opener.

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 usefully describes the result shape (one table of businesses with named fields) and where it lands (Puley history plus spreadsheet link). For a 4-parameter, open-world scraping tool it is nearly complete; only edge behavior such as empty results or what happens beyond 60 leads is unaddressed.

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 carries the full burden and does so: 'what' is explained with concrete examples (dentists, solar installers, wedding venues), 'where' specifies a city or area with its country, 'count' gives the ceiling (60) and timing, and 'min_rating' enumerates the accepted values (0, 3, 3.5, 4, 4.5). This is information the schema lacks entirely.

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 concrete resource and enumerates what each record contains (rating, reviews, phone, business email, WhatsApp, website, social profiles), which is far more specific than the bare name. It stops short of explicitly distinguishing itself from near-siblings like find_places or maps_rank, which also deal with places/business data.

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?

Usage is implied by the framing ('Local businesses to sell to, in one call'), which signals a lead-generation intent, and the parameter notes give practical constraints (up to 60 per call, ~1 minute). However there is no explicit when-to-use / when-not-to-use guidance and no named alternative among the many find_* siblings.

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