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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds substantial behavioral context beyond them: the ~15-minute upload cadence, the 07:00-23:00 Israel-time window, overnight retention with a 48-hour staleness cutoff, and the guarantee that the tool never contacts Kuze or creates a booking. That last point is critical, since openWorldHint=true could otherwise mislead an agent into assuming a side effect.

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 content is dense and nearly every clause earns its place, but it is delivered as one sprawling sentence with a long subordinate opening ('After applying the clinical routing and safety gate at https://...') that delays the actual operation. Front-loading the verb and result would materially improve scannability.

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?

With an output schema present, the description need not itemize return fields, and it still flags updated_at and the free-only guarantee. Freshness, retention, safety gating, and confirmation semantics are all covered; the only real gap is the unexplained filter parameters, which is a notable but bounded omission.

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 0% across 8 parameters, so the description must carry the burden and mostly does not. It explains the three-date limit that corresponds to max_results (const 3) and gestures at 'filtered to the request', but says nothing about language, from_date, after_time, before_time, patient_type, or time_preference — an agent must guess at how those interact with the three-date cap.

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 concrete artifact ('free_slots_snapshot: the available appointment times (only free times, never booked slots or patient data)') and its source, which is far more specific than the tool name alone. It implicitly separates itself from the booking sibling ('never confirms a booking'), but never names get_booking_handoff, so the differentiation is inferential rather than explicit.

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?

It gives an explicit prerequisite ('After applying the clinical routing and safety gate'), explicit exclusions ('EMERGENCY, REFER and OUT_OF_SCOPE block scheduling'), and explicit prohibitions ('Never infer availability from clinic hours or invent a missing date'). It also directs the agent to the official Kuze scheduler for verification, which is a clear when-to-go-elsewhere instruction.

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