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

Goes well beyond the annotations: it warns that a repeat call can create a duplicate booking, explains idempotency_key behavior, requires consent text be shown first, lists rejected email domains, states per-IP/per-shop rate limits and a daily cap, and defines the 2-hour/21-day start window. This is exactly the mutation-risk context an agent needs on top of destructiveHint=true.

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?

Dense single block, but front-loaded with the trigger condition and duplicate-booking warning, and every clause carries a rule the agent must apply. Some sentences duplicate the schema verbatim (ISO-8601 example, disposable-domain rejection), which is minor redundancy rather than padding.

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 12-parameter mutation tool with 7 required fields, it covers consent, validation, timing windows, deduplication, rate limits, and return values; with an output schema and destructive annotation present, nothing an agent needs to call this 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds cross-field semantics the schema does not: job_summary falling back to problem, service_area inference, address requirements per consult type, and offering/start provenance. It does repeat some schema content (start format, email rejection), which keeps it from 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 and resource ('book a local home-service appointment', 'Confirms a free consult when the slot is open'), which cleanly separates the consult flow from the general service flows. Sibling differentiation is partial: it explicitly references get_booking_status and get_business as supporting tools but never says when to prefer request_service or submit_service_request instead of this one.

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 a clear precondition ('has already chosen an open time') and an explicit alternative ('if unsure, check get_booking_status first'), both of which direct agent behavior. It stops short of naming the competing booking siblings as alternatives for non-consult cases, so routing is clear but not exhaustive.

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