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

This description goes far beyond the readOnlyHint annotation by explaining that hoursNow is present-tense and timezone-resolved, warning against interpreting weekday rows as 'open now,' and disclosing the Square sandbox/demonstration context engagement behavior. It also clearly states how unrecognized business names are refused rather than silently matched, which is critical behavioral context.

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 description is long but densely informative: core fields, present-tense warning, business roster, Square context, pipeline, and name resolution are all covered in a logical order. A little trimming of the downstream booking details would tighten it, but the structure is appropriate for the connector's complexity.

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 names all key returned fields (tagline, services/menu, hours, appointment grid length, hoursNow, bookable, schedulingSystem) and provides the exact workflow with biz_availability and biz_book. It also covers all three supported businesses, name resolution, and the refusal fallback, so nothing needed to call biz_info correctly is missing.

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?

The input schema already documents both business and businessId with 100% coverage, including name-or-id resolution, defaults, and short-form behavior. The description adds examples and repeats the resolution/refusal semantics, but it does not materially change or add parameter meaning beyond what the schema already provides.

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 clearly states what biz_info returns—tagline, services/menu with prices, weekly hours, appointment grid length, and today's hours—so an agent knows what resource and data are involved. It doesn't explicitly contrast a sibling like biz_menu or biz_availability in the purpose statement, but the field list and 'Call this first' pipeline make the tool's role clear.

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?

The description explicitly gives a workflow: 'Call this first, then biz_availability to see open times, then biz_book to take one,' which tells the agent when in the overall flow to use this tool. It does not directly address excluding siblings like biz_menu, but the sequencing and refusal behavior provide strong usage guidance.

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