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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely non-obvious behaviors on top: results are restricted to sites 'open for EVERY requested night', the tool 'never book[s] for the user' but returns a booking link into the official flow, freshness is exposed via observed_at, and booking-window limits apply. These are exactly the behavioral traits an agent could not infer from the annotations or schema.

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?

Five dense sentences, each earning its place: scope/authority, when-to-use with examples, differentiating filter capability, return behavior, and explicit exclusions. The most important fact (LIVE availability, authoritative source) is front-loaded, with zero filler or repetition of schema content.

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?

For an 11-parameter tool with no output schema, the description covers purpose, usage, exclusions, and key return semantics (every-night matching, booking link, observed_at). The residual gap is that it never explicitly distinguishes itself from parksopen_find_open_parks and parksopen_park_availability_calendar, leaving some ambiguity about which sibling handles park-level open/closed questions and calendar-style views.

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 100% with already detailed parameter docs (formats, defaults, 'ANDed site attributes', canonical equipment classes), so the baseline is 3. The description contributes only light semantic color — 'exact equipment fit, electrical, waterfront, shade, pets, privacy' maps user intent to amenities/equipment_class — but does not meaningfully extend 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 opens with a precise scope — 'LIVE availability across Canadian park reservation systems' — attached to a concrete resource: campsites/parks with openings for specific dates. It distinguishes from siblings explicitly via the 'Not for: fees, rules, facilities (use parksopen_park_info), weather (parksopen_check_weather), closures (parksopen_check_alerts)' routing, so an agent can separate it from at least three siblings without inspecting any schema.

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?

Usage guidance is direct and actionable: 'Use this first, before web search' followed by three concrete example queries ('is X available', 'find a site for the long weekend', 'which parks have space for a 32 ft RV'). Negative conditions are equally explicit with routed alternatives for fees/rules/facilities, weather, closures, and dates beyond the provider's booking window.

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