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

The description adds material behavioral detail beyond the annotations: it discloses that outcomes are 'delivered, held or failed' rather than a confirmed booking, and it spells out idempotent behavior ('Calling again with the same action_id returns the same outcome and sends nothing'). This complements the idempotentHint annotation and gives the agent a concrete mental model of side effects.

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?

Two sentences deliver the core action, a precondition, the outcome space, and idempotency behavior with zero filler. Every clause adds operational value and the most important constraint is front-loaded.

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 output schema exists, the description covers the essential context: precondition, outcome states, and repeat-call behavior. The main gap is not mapping 'consent_text' to the consent_version parameter and not explaining what distinguishes delivered, held, and failed outcomes, though that may be covered by the output schema.

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 only 17%, so the description carries more responsibility. It does add meaning to verification_code ('their code'), consent_version ('consent_text'), and action_id ('Calling again with the same action_id'), but it references non-existent term 'consent_text' instead of mapping clearly to consent_version, and it does not help with note, service_category, or preferred_window beyond what the schema already states.

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 names a specific verb ('Send'), a precise resource ('the started request'), and a target ('to the clinic'), with the precondition 'after the patient reads back their code and agrees to consent_text.' It also clearly distinguishes itself from a booking confirmation by stating the outcome is 'never a confirmed booking,' which separates it from the sibling confirm_xona_booking.

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 implies when to use it: after a request has been started and after the patient verifies their code and consents. It also excludes booking confirmation as a purpose. However, it does not explicitly name an alternative tool or state a when-not-to-use condition beyond 'never a confirmed booking,' so the guidance is clear but not fully explicit.

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