apple_maps_directions

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers richly. It details the exact return structure (route name, main/alternate flag, distance, durations, toll/highway flags, description, traffic note, turn-by-turn steps) and the effect of detail=full in adding leg path coordinates. It also discloses supported preferences and the transit limitation, which together paint a complete behavioral picture.

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 well-structured and front-loaded with the core purpose, then return details, then preferences, then the exclusion. However, the phrase 'driving, walking, or cycling' appears in both the first and second sentences, creating minor redundancy, and 'Apple Maps' is repeated. Despite this, every sentence earns its place and no non-essential filler is present.

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 no output schema, the description thoroughly explains return values, which is essential. It covers route-level fields, turn-by-turn step contents, the detail=full behavior, travel modes, time/departure preferences, and the transit limitation. Together with the 100% schema coverage, an agent has sufficient information to construct correct calls and interpret responses, making the description complete for the tool's 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds meaningful semantics beyond the schema. It explains what detail=full does (adds leg path coordinates), enumerates mode values (driving, walking, cycling) which the schema leaves as 'Travel mode', and explains the purpose of depart_at as 'traffic-aware estimates' and the avoid_* flags as mode-specific preferences. This goes beyond the minimal schema text.

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: 'Get Apple Maps driving, walking, or cycling directions.' It clearly states the tool returns routes between an origin and destination with optional stops, which distinguishes it from siblings like apple_maps_eta (ETA) and apple_maps_transit_departures (transit). The explicit 'Transit routing is not available' further disambiguates it from transit-related 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?

The description gives clear context about supported modes (driving, walking, cycling), preferences (departure time, avoid tolls/highways/stairs), and the detail parameter. It explicitly excludes transit routing, which tells an agent when not to use this tool. However, it does not name specific alternatives such as apple_maps_eta for time-only estimates or apple_maps_transit_departures for transit schedules, so it falls short of full when/when-not guidance.

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