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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial context beyond that: it explicitly states '**This tool does not create or confirm a reservation — it only generates a booking link.**' It also details response handling—including link_markdown usage, relaying guidance in the user's language, and the correct payment wording ('temporarily secured' vs. 'winning a race'). This discloses behavioral traits and response constraints that annotations do not cover, and it does not contradict any annotation.

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 every sentence carries instructional weight, covering usage conditions, response formatting, and parameter handling. It is front-loaded with the core purpose and usage condition. Some redundancy exists in repeated 'never' statements, but these serve as explicit prohibitions rather than filler. The structure is clear, though a more condensed version could achieve the same effect with less repetition.

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 presence of an output schema, annotations, and full parameter descriptions, the description is nearly complete for an agent to call the tool correctly. It covers when to call, what it returns (link and guidance), how to present results, and parameter omissions. Minor gaps include handling of invalid slugs or shop not found, but these are typically covered by the output schema and common error handling. The description is robust enough for its complexity.

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 covers 100% of parameters with descriptive text (e.g., items explanation about designated vs. capacity). The description adds value by clarifying when to omit optional parameters ('if the customer has not picked them yet, still call it with just the shop') and reinforcing that slug must come from search_shops. It also reminds that date/time/items are optional and that the customer chooses them on the booking page, which goes beyond the schema's basic descriptions.

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 opens with a specific verb and resource: 'Create a pre-filled Timeplex booking link (and booking card) for a selected Korean beauty or wellness shop and appointment.' It clearly distinguishes itself from siblings by stating it only generates a link and does not create/confirm a reservation, which separates it from request_booking. The 'selected shop' condition differentiates it from search_shops and search_availability.

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 explicit when-to-use and when-not-to-use guidance: 'Use this after the user has selected or clearly identified a specific shop' and contrasts with a bare category request that 'is NOT a selection — ask for the area and the booking conditions first.' It also instructs to never ask for permission, never withhold the link for missing date/time, and always call with just the shop if needed. This directly addresses alternative actions and conditions.

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