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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint, destructiveHint=false), so the description's added context is what counts: it discloses real-time data, the two supported systems, automatic name-to-ID conversion, and that an ambiguous name yields a candidate list rather than a failure. It stops short of auth, rate limits, or freshness/staleness details.

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?

Two sentences, no filler, front-loaded with the primary purpose. The scope constraint and the disambiguation rule each earn their place.

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 explain return values. It covers the two required parameters, the systems supported, and the ambiguous-name path, which is everything needed to call this correctly.

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 only 50% (city has an enum but no description), and the description compensates by mapping 'dc'/'nyc' to DC Metro and NYC Subway. For stationName it adds the ambiguity-handling behavior (multiple matches return candidates) on top of the schema's auto-conversion note, adding genuine value beyond the schema.

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?

States a specific verb and resource ('Get real-time train arrival predictions for a transit station') and immediately scopes it to DC Metro and NYC Subway, which implicitly separates it from the sibling get_sfbay_station_predictions and from get_bus_predictions/get_train_positions. An agent can identify the right tool from this line alone.

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 only implied: it's clear you call this for arrival predictions, but there is no explicit 'when to use this vs. get_sfbay_station_predictions' or any exclusion. The name-vs-ID and multi-match behavior is invocation guidance rather than tool-selection guidance.

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