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

Substantial disclosure beyond annotations: the 15-minute drop rule for trains without a departure, the hiding of departed trains unless include_departed is true, the lifecycle states including platform_withdrawn and due_now, absent fields meaning unknown, and times being London local with offset. It also warns predictions are unofficial and station screens are official — exactly the caveats an agent needs before acting on the data.

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?

Content is dense and largely front-loaded, but it arrives as one long run-on paragraph with deep parentheticals that interrupt the lifecycle explanation. It earns its length in information, though not in structure — bullet-style separation of lifecycle states would help.

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 no output schema, the description carries the return-shape burden and does so reasonably: platform, times, lifecycle states, absent-equals-unknown. What it does not address is anything about volume (how many departures typically, any cap) or ordering, which matters for a list-shaped read.

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 80%, so the baseline is high, but the description still adds real semantics for operator (case-insensitive partial name or short form, with examples) and for the behavior tied to include_departed. It leaves window_min's unit/meaning to the schema, which supplies min, max, and default, so the gap is small.

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 opening clause names a specific resource (departures), a scope (the next window), and the key payload (released or predicted platforms), so an agent knows exactly what it gets back. It does not differentiate itself from siblings like find_train or get_train, though the resource noun does most of that work implicitly.

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 is implied rather than stated: include_departed is explained and the operator filter is given examples, which tells the agent how to broaden results. But there is no explicit 'use this when / use get_track_record instead when' routing against the four siblings, so the agent must infer the boundary.

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