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

The annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety and repeatability are covered. The description adds the useful 'live'/real-time qualifier and lists what status fields are surfaced, but says nothing about what happens for an unknown station_id or about 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?

A single front-loaded sentence with the resource first and the returned fields after the colon. No filler, no repetition of the title.

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?

Since an output schema exists, the description needn't explain return values, and the live-status framing is enough on that front. However, for a 2-required-parameter tool with an entirely undocumented station_id, the definition leaves the agent guessing where that identifier comes from.

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%: network_id is documented inline (including its source tool), while station_id has no schema description whatsoever. The description does not mention any parameter and so fails to compensate for that gap, e.g. by explaining that station_id must come from nearby_stations or how it is formatted.

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 resource (one station) and enumerates the state it returns (bikes, e-bikes, free docks, rental/return capability), which clearly separates it from the list-style siblings search_networks and nearby_stations. It does not explicitly name those siblings, so it stops short of full disambiguation.

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?

"One station" implies the tool is for a known station id, which is useful implied guidance, but there is no explicit when-to-use vs. when-to-use-nearby_stations statement and no pointer to how a station_id should be obtained. Nothing actively misleading, just under-specified.

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 and openWorldHint, so safety behavior is covered. The description adds real value by disclosing that results carry live availability (bikes, e-bikes, free docks) and that the search is confined to a single network. It says nothing about ordering, distance units, or how the default limit/distance caps behave.

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 with no filler. The what-it-returns content is front-loaded and the prerequisite follows, which is the right order for an agent skimming for capability first, then constraints.

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?

An output schema exists, so return-value detail is unnecessary here, and annotations cover the safety profile. For a 6-parameter spatial query the remaining gaps (distance units, result ordering, default limit behavior) are modest but real.

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 33%, so the schema documents just 'need' and 'network_id' while lat, lon, limit and max_distance_meters are bare. The description compensates partially by framing the operation as 'nearest ... to a point,' which gives meaning to the coordinate pair and the distance-based ranking, but it adds nothing for limit or max_distance_meters beyond their self-descriptive names.

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 ('Nearest stations of one network to a point') plus what the result carries ('live bikes, e-bikes and free docks'), which is far more than the name alone. It implicitly separates itself from search_networks by naming it as a prerequisite, but never explicitly contrasts itself with the other sibling, get_station.

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?

Gives a concrete prerequisite and call ordering: 'Get network_id from search_networks first,' which is the key sequencing decision for an agent. It stops short of stating exclusions or when to prefer get_station for a single known station, so no 5.

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 and openWorldHint, so the safety profile is covered. The description adds one genuinely new behavioral fact — that results include unsupported networks with a reason — but says nothing about ordering, result count behavior, or how the limit interacts with that unsupported list.

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 short sentences with no waste; the core search capability is front-loaded and the return-value note follows immediately. Nothing could be removed without losing routing or contract information.

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?

An output schema exists, so return-shape detail is unnecessary, and the description still flags the non-obvious 'unsupported + why' payload. The only gap is the unexplained limit parameter (default 5, max 20), which matters for an open-world search that may match many networks.

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 50%: 'query' is documented in the schema itself, and 'limit' carries only min/max/default with no prose. The description's 'by city, area or name' merely restates the query parameter's own description and adds no meaning for 'limit', so the schema is doing essentially all the work.

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 ('Find docked bike-share networks') and enumerates the matching dimensions (city, area, name). It also clarifies the output contract ('network ids') and the downstream tools it feeds, so an agent knows exactly what this tool produces versus the station-level siblings.

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?

By saying it returns network ids 'for nearby_stations and get_station', it implicitly establishes itself as the prerequisite discovery step before those tools. That is clear contextual guidance, though it never states explicit exclusions or when not to use it (e.g., if you already have a network id).

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