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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety and openness profile is covered structurally. The description adds scope context (validity dates, licence/attribution metadata) beyond the annotations, but says nothing about response format, freshness of the data, or why open-world behavior matters here. Adequate but not rich.

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?

A single compact sentence with no redundancy, and the most important content (which feeds are loaded) is front-loaded. The telegraphic noun-phrase style is slightly less readable than a full sentence but costs no extra tokens.

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 zero-parameter, read-only metadata tool with no output schema, the description effectively does the work of documenting the return payload by naming the fields the agent will get back. It would be complete if it also signalled that no arguments are accepted, but overall it covers what an agent needs to call it.

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?

The tool takes zero parameters, so there is no parameter semantics to explain, which is the baseline-4 case. Nothing in the description misleads about inputs.

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 names a concrete domain and enumerates the exact content returned: loaded carriers/feeds, validity dates, licences, required attribution, and enable-able feeds. It is clearly distinguishable from the journey/departure/stop siblings, though it is written as a noun fragment rather than a verb-led statement of what the tool does.

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?

There is no explicit when-to-use guidance, no prerequisites, and no named alternatives. The phrase 'which feeds can be enabled' hints at a provenance-checking workflow before plan_journey, but the agent must infer that entirely; nothing in the text tells it when this tool is the right choice over the siblings.

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=true and openWorldHint=true, so the safety and external-data profile is covered. The description adds useful content by listing what the board surfaces (live delay, platform, main stops) and the direction filter, but says nothing about freshness of 'live' data, rate limits, or result ordering.

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, front-loaded with the core purpose and followed by the optional scoping filter; no filler. The field enumeration is dense but earns its place by telling the agent what comes back.

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 9-parameter read-only board with strong schema coverage, the description adequately covers what the tool returns and the main optional filter. Remaining gaps (live-data freshness, pagination beyond the default limit) are largely handled by the schema defaults.

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 89%, so the schema already documents nearly every parameter including date formats, mode enums, limits and the time window. The description only echoes the direction filter ('services going towards a given place'), adding little beyond what the schema states.

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 states a specific verb+resource: a departure/arrival board for a named station or stop, and enumerates the fields returned (time, delay, line, platform, destination). It implicitly distinguishes itself from siblings like find_stops and nearby_stops, though it never names 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?

Usage is implied — use it when you know the station and want its board — and the direction filter is flagged as optional. There is no explicit when-not guidance or pointer to alternatives such as plan_journey for full itineraries, 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.

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful behavior beyond that: fuzzy matching, diacritics being optional, and the fields returned (modes, coordinates, source feeds), which is valuable since there is no output schema. It stops short of describing result ordering, limits, or what an empty match looks like.

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 compact sentences with no filler. The core action is front-loaded, and the parenthetical detail and return-field note are tightly packed into the second clause.

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 three-parameter read-only search with no output schema, the description covers the action, matching semantics, and return fields. What is missing is limit/default behavior and routing to the sibling tools, but no output schema exists so return documentation need not be exhaustive.

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 67%: query and modes are documented in the schema, while limit (1-50) has no description anywhere. The description adds real semantic value for query by specifying fuzzy matching and diacritics behavior, which the schema does not, so it slightly compensates but does not close the limit 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?

The description states a specific verb and resource ('Search stations/stops by name') and qualifies the matching semantics as fuzzy with optional diacritics. It implicitly contrasts with the proximity-based sibling nearby_stops by emphasizing name matching, but never names that alternative 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?

Usage is only implied: the 'by name' qualifier suggests when this is appropriate versus nearby_stops, but there is no explicit when-to-use, when-not-to-use, or named alternative. An agent must infer the routing from the sibling list.

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 operation read-only and open-world, so the safety profile is covered. The description adds that results are spatial and tied to coordinates, but omits result limits, pagination, or whether all modes are included by default.

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 definition is a single front-loaded sentence with no wasted clauses. It is appropriately brief for a simple lookup, though the absence of any second sentence leaves useful context unstated.

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 relatively simple spatial tool with annotations and no output schema, the description is minimally adequate. It implies the return type (stations and stops) but does not cover filtering behavior or practical limits, leaving some gaps for an agent invoking it.

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?

With only 50% schema description coverage and no parameter details in the description, the text mentions coordinates and a radius only conceptually. It does not explain the modes filter, radius defaults/bounds, or coordinate constraints, adding little 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?

The description states a clear resource (stations and stops) and spatial scope (within a radius of coordinates), which distinguishes it from generic stop lookups. It does not explicitly differentiate itself from sibling tools like find_stops, so it falls short of a 5.

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 parenthetical 'e.g. after geocoding an address' implies a common workflow, but the description never states when to use this tool versus find_stops or how it complements plan_journey. Usage context is only implied, not explicit.

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 declare readOnlyHint and openWorldHint, so safety is covered externally, and the description adds genuinely useful behavior: the return payload (times, platforms, operators, changes) and the time-sensitivity caveat that live delays only apply 'today'. It also discloses the Poland-only coverage boundary, which is not in any structured field.

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 dense sentences with no filler; the core capability leads and the return/time-sensitivity details follow. Every clause carries information an agent needs to select and call the tool.

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 10-parameter, no-output-schema tool with only two annotations, the description adequately covers scope, accepted inputs and the shape of the result. It does not address no-connection or error outcomes, and transfer/arrive_by semantics are left entirely to the schema, but nothing essential to correct invocation 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 description coverage is 100%, so the schema already documents every parameter including formats, defaults and enum values for 'modes'. The description largely restates the from/to input forms ('station name', 'town', coordinates) already present in the schema properties, with only the 'Zakopane = all its stops' clarification adding marginal meaning.

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 ('Find connections between two places in Poland') and immediately scopes it to multi-modal routing including train/bus changes, which clearly separates it from siblings like departures and trip_details. The geographic scope (Poland) and the accepted origin/destination forms are stated up front.

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 declared: the description positions this as a point-to-point planner, so an agent can infer it is the right tool for route planning versus departures/trip_details. However, no sibling is named and no when-not-to-use condition is given, so routing is left to inference.

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=true and openWorldHint=true, so safety and external-data exposure are covered structurally. The description adds that results include live delays and cancellations, which is useful behavioral context about data freshness, but it says nothing about error behavior, ambiguity handling, or rate 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?

Two sentences: the first front-loads what the tool returns, the second explains how to identify the trip. No filler, and the most decision-relevant information (output contents) comes first.

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 correctly carries the burden of describing the return payload (stops, times, platforms, live status). It does not address what happens if neither `ref` nor `train` is supplied, nor the meaning of the `live` flag, leaving minor gaps for a zero-required-parameter tool.

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 75%, so the schema already documents `ref`, `date`, and `train`. The description still adds value: it explains where `ref` comes from and gives accepted train formats ('3510', 'IC 3510', 'Podhalanin'), clarifying matching semantics. The `live` boolean remains undocumented in both places, which caps this below 5.

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 names a specific resource (all stops of one train/bus run) and enumerates the returned fields (times, platforms, live delays/cancellations), so the agent immediately knows what this returns versus the summary-level sibling tools. It also points at plan_journey/departures as the origin of the `ref`, distinguishing it from those 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?

It gives two concrete ways to identify the trip — by `ref` from plan_journey/departures, or by train number/name plus date — which is real invocation guidance. It stops short of stating when *not* to use it (e.g., for journey planning, use plan_journey), so it lacks explicit exclusions.

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