Faceabot Transit Norway (Vy, Entur)

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so safety is covered. The description adds value beyond that by disclosing data currency ('live delays, cancellations'), transport-mode and operator breadth (Vy, SJ Nord, Go-Ahead, Ruter, Skyss), and the richness of each result. It omits auth needs and rate limits, but the added data-quality context is meaningful.

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?

Three tight lines following a clear purpose / 'Use when:' / example structure, all front-loaded with zero filler. Every sentence and token earns its 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?

For a 6-param, no-output-schema tool with full annotations, the description effectively describes the return content (times, platforms, transfers, delays, cancellations) and scope, leaving little an agent must infer. Remaining gaps (no per-param detail for results/time_is) are minor.

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 67%, so the schema already documents from/to/date/time; the description's example ({"from":"Oslo S","to":"Bergen stasjon"}) only supplies sample values for the two required params. It adds no semantics for time_is or results, and given a mid-range coverage figure the baseline of 3 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?

States a specific verb+resource: journeys between two places in Norway, enumerating transport modes (train, bus, tram, metro, boat) and operators, plus the return content (times, platforms, transfers, delays, cancellations). This clearly differs from the sibling no_station_departures (a departures board) and no_find_station (station lookup), though it does not name them explicitly.

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 'Use when:' line gives an explicit trigger (someone travels by public transport in Norway) with a concrete example (Oslo to Bergen). It stops short of naming alternatives or stating when NOT to use it versus the departures/station siblings, so it is strong context without routing exclusions.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety/lifecycle profile is fully covered by structured data. The description adds only that results carry ids, which is mild output context; it says nothing about matching semantics (prefix vs. substring) or result limits.

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?

Three short, front-loaded lines: purpose, trigger condition, example. Every element earns its place with no filler.

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 a single-parameter lookup with no output schema and rich annotations, the description covers what the tool does, when to call it, and that ids come back. Only the exact matching semantics are left implicit.

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% and there is only one parameter, so the schema already documents `query`. The description's "matching a word" and the example add a small amount of intuition about matching behavior, but the baseline of 3 applies when the schema does the heavy lifting.

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 ("Finds") and resource ("Norwegian stations and stops"), plus the key output ("with their ids"). It doesn't name siblings, but the siblings (departures, connections) are functionally unrelated lookups, so disambiguation is not really needed.

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?

Explicitly gives the trigger condition — "Use when: a place name is ambiguous or misspelled" — and reinforces it with a concrete example query. No when-not guidance or named alternative is given, but for a lookup helper that is a minor gap.

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

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

Annotations already declare the safe, read-only, idempotent, open-world profile. The description adds the return payload—time, line, destination, platform, live delay, cancellations—which is valuable given there is no output schema. It omits auth, rate limits, and cancellation semantics, but annotations lower the burden.

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 crisp sentences plus a useful example; every element is front-loaded and relevant. No redundant text.

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 a simple two-parameter read tool with annotations covering safety and no output schema, the description is nearly complete: it lists return fields, usage context, and an example. The only omission is any guidance on the results count, which is minor.

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 50%: the station parameter is documented in the schema, but results (count) is not described anywhere. The description supplies a concrete example for station and clarifies 'one station or stop', but it never mentions the results parameter or its default/maximum. It adds some value but does not compensate for the coverage gap.

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 'Next departures' and resource 'Norwegian station or stop', lists transport modes, and makes clear it returns departures from a single stop. It does not explicitly contrast with siblings no_connections or no_find_station, so an agent must infer the distinction from scope wording ('one station or stop').

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 line 'Use when: someone is at (or going to) a stop in Norway' gives clear context for when to call. No when-not condition or alternative tool is named, but the usage context is explicit.

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