Map Parser

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

The description adds valuable behavioral context by specifying that it 'Returns the file contents,' which informs the agent how the output will be consumed, a detail not covered by the readOnlyHint annotation. This clarifies the nature of the output as data rather than a URL to a file.

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 concise and highly efficient, using two clauses to explain the input flexibility (link OR list of stops) and the resulting output formats (CSV or KML). No sentence is wasted.

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?

The description provides all necessary contextual information for the tool to be used correctly, including the nature of the inputs and the functional utility of the outputs. Since there is no output schema, the description successfully addresses the result of the call.

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?

Despite 33% schema description coverage gap, the description provides rich semantic meaning for the 'format' enum parameter by explaining the functional utility of both CSV (Google My Maps import) and KML (Google Earth, My Maps). This adds critical context beyond just listing the allowed strings.

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 clearly states the core purpose: converting inputs (maps link or list of stops) into structured file formats (CSV/KML). It distinguishes itself by the 'export' action and the specific output formats, which differentiates it from sibling tools like 'geocode' or 'parse_map_link'.

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 implies usage when the user requires a transferable file format (CSV/KML), but it doesn't explicitly state whether to use this tool before or after another sibling tool like 'parse_map_link'. The guidance is sufficient but not prescriptive.

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?

The annotations already establish that this is a read-only, open-world lookup. The description adds useful behavioral context by naming OpenStreetMap Nominatim and describing the return shape as a "State, Country code" region plus full address. It does not mention rate limits, no-result behavior, or provider attribution requirements, which keeps it from a 5.

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 front-loaded with the core action and covers the two modes and return value in two tight sentences. There is no redundant or filler language.

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 geocoding tool with no output schema, the description gives enough context about modes, provider, and return values for an agent to call it correctly in most cases. The main remaining gap is that the mutually exclusive input combinations and no-result behavior are not stated.

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 only 33%, with only the query parameter documented in the schema. The description compensates partially by mapping place name/address to forward lookup and coordinate to reverse lookup, but it does not explicitly name lat/lng, clarify that both are needed for reverse geocoding, or state that query and coordinates are alternative 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 uses a specific verb, "look up," and names both supported modes: forward place/address lookup and reverse coordinate lookup. It also names the underlying provider and the returned region/address, so an agent can distinguish it from sibling tools such as get_route or parse_map_link.

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 signals when each mode applies: use a place name or address for forward geocoding, or a coordinate for reverse geocoding. It does not explicitly compare against sibling tools or state exclusions, but the usage context is clear enough for selection.

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 value the annotations do not: the external routing engine (OSRM) is named, and the result structure "per leg and in total" is disclosed, which matters because there is no output schema. It omits limits (max 25 stops), error modes, and rate/usage expectations for the external service.

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, both front-loaded: what the tool computes and returns first, the calling convention second. No filler, no restatement 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?

With only 2 parameters, no output schema, and strong annotation coverage, the description does enough: it explains the return shape and the waypoint source. The gaps are the unmentioned mode parameter and the stop-count limit, which an agent would only find by reading the schema.

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% – the mode enum is self-documenting in-schema, but waypoints carries no per-field descriptions. The description partially compensates by implying order sensitivity ("in order") and by pointing to parse_map_link for the waypoint shape. It never mentions mode, the 2–25 item bounds, or lat/lng semantics, so the description adds only partial meaning over 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 first sentence names a specific computation (distance and travel time), the resource (a route through ordered stops), and the granularity of return (per leg and in total). It also names the upstream sibling parse_map_link, so an agent can place it in the workflow. It does not explicitly contrast with export_waypoints, so it stops short of full sibling differentiation.

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?

"Pass the waypoints from parse_map_link" gives a concrete precondition that ties this tool to one specific caller, which is real routing guidance. It is silent on when NOT to use it (e.g. single-waypoint cases that geocode would serve, or exporting via export_waypoints), so there are no stated alternatives or 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 only declare readOnlyHint and openWorldHint; the description adds genuinely new behavior — short-link expansion, headless-browser fallback for obscured stop names, and an explicit latency warning of up to a minute. That latency disclosure is exactly the kind of context an agent needs to plan a call.

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 what is returned and followed by the operational caveats. No filler and nothing repeated from the schema.

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?

Output shape is described (stops with names/coordinates, plus region) and there is no output schema to defer to, so this is close to complete. It doesn't cover failure behavior for malformed or non-directions links, which would matter for an open-world 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 100%, so baseline would be 3, but the description amplifies the useBrowser parameter by tying browser mode to its cost (slow, up to a minute). The url parameter's accepted forms are already fully documented in 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 precise verb and resource: extracts stops (names + coordinates) and the likely region from a Google Maps directions link. The resource (a shareable URL) is distinct enough from geocode/get_route that an agent can select it, but the description never names or contrasts those siblings 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?

Gives clear context for when the tool applies (a Google Maps directions link, short or full) and explains how hidden-name links are handled, including that browser mode is slow. It stops short of stating when to prefer get_route or geocode over parsing a link.

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