fetch_road_network

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

No annotations are provided, so the description carries the full burden, and it delivers comprehensively. It discloses the fixed endpoint, the 30-second timeout, 25 MB response cap, fail-closed behavior on Overpass errors, bounding box validation and caps, result capping and pagination, caching of identical requests, and its pure-read nature affecting no state. It even includes licensing attribution. This is far beyond the minimum and leaves no major behavioral surprise.

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 description is long but every sentence carries distinct information—purpose, waterway addition, validation/caps, technical constraints, caching, licensing, and read-only nature. It is front-loaded with the core purpose and then layers details. The structure is logical and there is minimal redundancy. It could arguably be tightened, but for a tool of this complexity (8 parameters, dual output types, pagination), the length is justified. Only a minor reduction in verbosity would earn a 5.

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?

There is no output schema, so the description must fully explain what the tool returns, and it does: it specifies the exact attributes for roads (way id, name, highway type, geometry, length, and optional tags) and for waterways (way id, name, class, geometry, length, and width/intermittent/tunnel). It also covers error handling, defaults, paging, and caching. An agent has everything needed to invoke the tool correctly and interpret the result without any further reference.

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?

While schema description coverage is 100%, the description adds substantial semantics beyond the schema. It enumerates the default roadTypes set, states that unknown values are rejected (never silently dropped), specifies the allowed waterway types ('river/stream/brook/canal/drain/ditch'), clarifies that roads and waterways are paged independently with the same offset/maxResults, and describes the output structure under `roads` and `waterways`. This transforms the parameters from bare field names into actionable guidance on how to compose valid requests and interpret results.

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 starts with a specific verb ('Fetch') and resource ('road network for a geographic bounding box from OpenStreetMap'), and immediately distinguishes it from any other geocoding or URL-based fetching by stating the fixed Overpass endpoint and excluding Nominatim and caller-supplied URLs. It also clarifies the output is 'structured road geometry and attributes for future EPANET network generation', differentiating it from sibling tools like generate_network_from_bbox which would perform downstream generation. This makes the tool's scope unmistakable.

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 description clearly implies usage as a data-fetching step for later EPANET generation ('for future EPANET network generation') and emphasizes it is read-only ('PURE READ: no network session, model, or file is touched — nothing is generated or optimized yet'). While it does not explicitly name alternative tools or state 'when not to use', the context of the sibling list and the explicit read-only note makes its role clear. It stops short of an explicit routing instruction but is strong enough that an agent would know when to choose it.

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