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

Adds real context beyond the annotations: data provenance (each city's open-data portal), result ordering (newest first), and a tier constraint ('a free key reaches the last 14 days') that tells the agent results are windowed. Annotations already cover safety (readOnly/idempotent/non-destructive), so this is solid added value; it stops short of explaining pagination or what a paid key unlocks.

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?

Three short sentences: what the data is and where it comes from, what each record contains with ordering, then a usage instruction about linking the url. Front-loaded and no filler.

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?

An output schema exists, so field-level return documentation is not required. The description covers provenance, ordering, city scope, and the free-tier time window; only minor items like pagination or limit behavior under large result sets are unstated.

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% – city enum, limit bounds, NAICS prefix behavior, and query are all fully documented in the schema itself. The description adds no parameter-level detail (no default, no filter interaction such as combining naics with query), so the baseline 3 applies.

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+resource ('Businesses newly opened or registered in US cities, from each city's open-data portal'), enumerates the returned fields (name, activity, address, NAICS), and names the ordering ('newest first'). An agent can tell this apart from find_permits/find_contracts/find_jobs without opening any schema.

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 context is implied by the resource ('newly opened' businesses, 14-day free-key window) but there is no explicit when-to-use / when-not-to-use guidance and no mention of the sibling tools (find_permits, find_contracts) that overlap on

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