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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds significant behavioral detail beyond that: availability flags per segment, that legs[].options are independent and not filtered against each other, that connection validity is not pre-filtered server-side, and that the widget enforces it. These are non-obvious behaviors that the agent must know to interpret results correctly. No contradiction with annotations.

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 longer than average but every section earns its place. It front-loads the core purpose and then uses bullet points to clarify leg patterns. The connection-validity caveat is important and placed at the end. It is structured and readable, not verbose or repetitive. Slight deduction for length, but justified by the tool's complexity.

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 complexity of multi-leg searches, the description covers all critical operational details: leg ordering, human-readable location names, independent option reporting, and the lack of server-side connection filtering. It also clarifies that the widget enforces connections, which prevents the agent from over-promising. With an output schema present, the description needn't detail return fields. Nothing an agent needs to call this correctly is missing.

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 coverage is 100% for the only parameter (legs), and the schema itself provides detailed descriptions with examples. The description adds further semantics by explaining the leg chain patterns (one-way, round-trip, island-hop), reinforcing that locations are human-readable rather than port codes, and clarifying the chronological ordering constraint. This adds value beyond the schema, so a 4 is appropriate.

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: 'Search ferry trips as an ordered chain of 1 to 5 legs.' It clearly distinguishes itself from sibling tools by specifying human-readable location names instead of port codes and by covering multi-leg chains (one-way, round-trip, island-hop). This goes beyond a generic statement and fully differentiates it from tools like get_direct_connections_for_ports and search_trips.

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 provides strong usage context: it explains when to use it (one-way, round-trip, multi-leg) and explicitly states that there's no need to call get_ports first. It also describes the constraints on leg ordering. It does not explicitly name alternative tools or say 'use X instead,' but the context is clear enough for an agent to decide. A small deduction for not explicitly excluding cases better served by a sibling.

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