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

The description goes beyond the annotations by disclosing that this CREATES A REAL BOOKING and emails a confirmation with links to cancel or reschedule. It also warns about side effects (real booking) and the need to re-check availability if the time has passed. The annotations already indicate readOnlyHint=false and idempotentHint=false, but the description adds crucial context about the real-world impact and email notification, which is valuable for an agent deciding whether to invoke this tool.

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 concise and front-loaded. The first sentence states the core purpose and the critical side effect (real booking). The following sentences provide essential guardrails without unnecessary detail. Every sentence earns its place, and the warning about re-calling find_consultation_times is a useful, actionable note. It is well-structured and appropriately sized for a tool with 12 parameters.

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 the tool's complexity (12 parameters, nested objects, real-world side effects) and the absence of an output schema, the description is remarkably complete. It covers the purpose, the critical side effects, the prerequisites, the constraints on parameters, and the fallback behavior. The schema covers parameter details, and the description covers the behavioral context. Nothing an agent needs to call this tool 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 schema already has 100% description coverage for all 12 parameters, so the baseline is 3. The description adds extra meaning by explaining the relationship between parameters (e.g., 'hostId returned with that slot', 'startTime exactly as find_consultation_times returned it', 'timezone same one used to find the time') and by emphasizing that email and phone must be the person's own and never guessed. This adds value beyond the schema, so a 4 is appropriate.

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 the tool's purpose: booking a real meeting on Upforge's calendar for a person at a time they picked. It uses a specific verb ('book'), names the resource ('Upforge's calendar'), and explicitly distinguishes it from the sibling find_consultation_times by emphasizing it creates a real booking. This makes it easy for an agent to understand what the tool does and how it differs from related tools.

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 provides explicit when-to-use guidance: only call it after the person has chosen a time and agreed to be booked, with their own details. It also gives clear exclusions: never invent contact details, never book a time they didn't pick, and if the time has gone, call find_consultation_times again. This is strong usage guidance that leaves little to inference.

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