Roamward MCP

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds 'zero Mapbox cost' and licensing terms, which are useful but not critical. It does not describe error behavior or response format, but annotations cover the safety profile adequately.

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 first sentence about coverage is extraneous and not directly related to the tool's function. The description could be more concise by removing irrelevant marketing information and focusing on what the tool returns.

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?

Given the tool has one parameter and no output schema, the description lists key return fields (frozen corridor, ranked detour shelf, etc.), which is helpful. However, it lacks information on error handling or response structure, making it adequate but not complete.

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 schema covers 100% of parameters with a description for 'slug'. The tool description adds no additional semantics about the slug parameter, so it meets the baseline but does not exceed it.

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 'Returns the frozen corridor, ranked detour shelf, adjacent drives, and plan URL' which indicates the tool retrieves drive details, but the opening sentence about coverage is irrelevant and muddles the purpose. It does not explicitly differentiate from sibling tools like list_drives or search_stops.

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 mentions usage restrictions ('individual-assistant use with attribution') and licensing for bulk use, but does not provide guidance on when to use this tool versus alternatives. No context on prerequisites 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?

The description adds significant context beyond annotations: it lists drives at zero Mapbox cost, covers US regions with growing waves, and specifies shelf-reviewed status. It also warns about licensing for bulk extraction, aligning with readOnly/ idempotent hints. No contradiction with annotations.

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 informative but includes some extraneous marketing language (e.g., 'strongest in the West and Southwest') that may not be essential for tool understanding. It could be more concise by focusing on core functionality and usage guidance.

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?

Given no output schema and zero parameters, the description adequately explains what the tool returns (a list of published drives) and notes cost and licensing. However, it does not describe the structure of the list (e.g., fields returned, pagination), which would be helpful for complete understanding.

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?

There are zero parameters in the input schema, and schema description coverage is 100%. The description adds no parameter info, but none is needed. Baseline of 4 is appropriate for a parameterless tool.

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 it lists published, shelf-reviewed drives, using the verb 'lists'. The title and description together specify the resource (drives) and scope (published, shelf-reviewed). It distinguishes from siblings like get_drive (single drive) and search_stops.

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 mentions it is for 'individual-assistant use with attribution' and notes licensing for bulk use, but does not explicitly compare to siblings or state when not to use this tool. Usage context is implied but lacks clear when-to-use vs. when-not-to-use guidance.

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?

Adds behavioral details beyond annotations (e.g., zero Mapbox calls for published pairs, degradation to alternatives). But does not clarify behavior for parameters like hideKinds or detourBudgetMinutes.

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?

Reasonably concise but front-loaded with coverage info rather than the tool's primary action. Licensing notice adds length without aiding immediate understanding.

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?

Missing key context: what the output looks like, how to use parameters, and how this tool differs from get_drive/list_drives. Coverage and licensing info is tangential.

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 0% and the description provides no explanation of any parameter (from, to, hideKinds, detourBudgetMinutes). Fails to add meaning beyond schema structure.

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 does not explicitly state what the tool does; it discusses coverage and API call behavior but never says 'plan a drive' or similar verb+resource. The title provides context, but the description itself lacks a clear action statement.

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?

No guidance on when to use this tool versus siblings like get_drive or list_drives. Mentions usage restrictions ('individual-assistant use') but no comparative context for tool 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 indicate read-only and idempotent. The description adds behavioral details: exact-first, category-aware scorer, max 10 stops, and coverage disclaimer. No contradictions.

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 sentences with no waste: first sentence sets coverage, second explains scoring and limits, third covers licensing. Front-loaded with key info.

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 could mention return format, but it does specify max 10 stops and scoring behavior. Adequate for a search tool. Could add what fields each stop contains.

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 'query' parameter lacks description in schema but the description hints at its matching behavior. The 'state' parameter is explained. The description adds some meaning beyond 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 clearly states it searches for stops across US published drives, using a specific scorer, and returns up to 10 stops. It distinguishes from siblings (get_drive, list_drives, plan_drive) which are not stop search 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?

States usage is for individual-assistant use with attribution, and warns against bulk/commercial without license. This provides clear context for when and how to use, though it doesn't explicitly compare to alternatives.

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