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

Annotations declare readOnlyHint=true and openWorldHint=true, but the description adds substantial behavioral context: it calls the provider live, fails closed on provider failure, returns time windows based on bookingStartPolicy, and explains capacity behavior for multi-participant services. This goes well beyond the annotations and is critical for correct invocation and interpretation of results.

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 detailed but well-organized: it leads with the primary purpose, then covers behavioral nuances, and ends with a conditional usage rule. Each sentence contributes meaning, though it could be slightly tightened. It is appropriately front-loaded and not redundant.

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?

Given there is no output schema, the description explains what the tool returns (time windows) and the constraints on those windows (bookingStartPolicy, capacity). It also covers failure behavior, prerequisites (booking enabled), and a fallback action. For a read-only availability check, this is fully complete.

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 describes all three parameters (date, slug, serviceName), but the description adds crucial usage guidance, especially for slug: 'Copy it verbatim' and specifies it comes from search_businesses or get_business_info. This extra instruction reduces ambiguity and prevents common errors.

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 states a specific action ('check available appointment slots'), a specific resource (a service at a local business on a given date), and clearly distinguishes from siblings like book_appointment (which is for booking) and find_next_available_appointments (which is for finding next availability). It is precise and unambiguous.

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 gives an explicit condition for when to call ('ONLY call this if the business has 'booking' in its enabledFeatures array') and when not to, with an alternative ('share their contact info from get_business_info instead'). It also notes the tool fails closed, which sets expectations for error handling. This is exemplary usage guidance.

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