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

The description discloses a significant side effect beyond the annotations: it 'email[s] the patient a link to tap' and tapping it texts them a second link, so the agent knows calling this tool will contact the patient. It also clarifies the state boundary with 'Nothing is booked yet'. No contradiction exists; the mutation implied by holding a slot aligns with readOnlyHint: false and destructiveHint: false.

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?

Four short sentences with the core action front-loaded ('Step 1 of 2. Hold one open time...'). Every sentence earns its place: flow position, core function plus side effect, precondition, and a clarifying statement about what has not yet happened. Zero waste.

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?

The description covers the multi-step placement, the side-effectful email/text behavior, and the precondition, which is substantial for an 11-parameter tool. Since an output schema exists, return values don't need description coverage. The main gap is hold lifecycle details (expiry or what happens if the patient never taps the link), but that doesn't block correct invocation.

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?

With only 36% schema coverage, the description partially compensates: the two-link mechanism explains why patient_email and patient_phone are required and their distinct roles, and 'all of the patient's details' groups the personal-info parameters. However, practice_slug, service_id, and slot_fingerprint remain undocumented in both the schema and description, so the gap isn't fully closed.

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: 'Hold one open time with all of the patient's details' plus the email/text link flow. 'Step 1 of 2' and 'Nothing is booked yet' position it against confirm_xona_booking as the hold phase rather than the booking phase. This is specific, non-tautological, and clearly distinguishes it from sibling 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?

'Step 1 of 2' provides explicit sequencing context, and 'Ask for every detail before calling' is a concrete precondition telling the agent when it is ready to invoke the tool. It doesn't explicitly name alternatives or exclusion cases, but the two-step framing and the 'Nothing is booked yet' caveat give clear situational guidance.

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