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

Goes well beyond the readOnly/idempotent annotations: no booking or hold is created, no provider-confirmed availability exists so date results are conditional, starting prices are not guaranteed quotes, deposit is advance payment rather than an added charge, and ordering is geographic/alphabetic rather than a quality signal. These are exactly the misconceptions an agent would otherwise form.

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 routing instruction and purpose are front-loaded, and the dense sentences carry real information. It is still a long block covering caveats, pagination, and edge semantics in one sweep, so a reader must parse several lines before reaching the operational rules.

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?

For a 10-parameter decision tool with no output schema, the description pre-describes the return shape (options/uncertain/excluded groups with per-fact sources and dates, known subtotal, unresolved charges, next actions) and the limits of that data. Nothing an agent needs to call it correctly or interpret the result 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?

Schema coverage is 80%, so the baseline is 3, but the description adds meaning the schema does not: the pagination contract ('use next_offset across all three result groups') fills the undescribed offset parameter, and it clarifies that selected_addons means only user-requested extras since mandatory ones are auto-added. It does restate some enum content already present in the schema, keeping it short of a 5.

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 ('Compare a supported service intent') and immediately frames the goal: 'START HERE for choosing a service under a budget, with extras, or on a date.' It explicitly separates itself from the name/address lookup sibling (search_merchants), so an agent can route without opening either 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?

Gives an explicit alternatives rule ('use search_merchants for name/address lookup; use this tool for the service decision') and negative guidance on unsupported filters (time-of-day, stylist, hair-length) that must be deferred to merchant confirmation. It also flags that require_availability cannot be satisfied today, which prevents a predictable misuse.

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