Roamward MCP

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

Annotations (readOnlyHint, idempotentHint, destructiveHint) are already present. The description adds value by specifying the exact outputs: frozen corridor, ranked detour shelf, adjacent drives, and plan URL, plus a note about zero Mapbox cost. No contradictions 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 contains four sentences but the first sentence about coverage is superfluous and seems like marketing. The rest is functional but could be more streamlined.

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 tool with one parameter and no output schema, the description adequately explains what is returned and usage restrictions. It lacks explicit authentication or rate limit info, but annotations cover idempotency and read-only nature.

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?

Only one parameter (slug) with 100% schema description coverage. The description does not add further explanation beyond 'Published /drives slug.' Baseline is 3; no extra value provided.

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 title 'Get one published Roamward drive' and description 'Returns the frozen corridor...' clearly state a specific verb and resource. However, the opening sentence about coverage is distracting and doesn't clarify the tool's purpose. Sibling tools like list_drives and plan_drive help differentiate.

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 includes usage constraints: 'For individual-assistant use with attribution' and licensing terms for bulk/commercial use. However, it does not explicitly explain when to use this tool over siblings like list_drives or search_stops.

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?

Beyond annotations (readOnly, idempotent), the description adds behavioral traits: US coverage, zero Mapbox cost, licensing requirements for redistribution. This informs the agent about cost and legal constraints.

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 relatively concise but front-loads coverage rather than core purpose. It is structured well but could be more direct.

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 simple parameterless tool, the description provides sufficient context: coverage, cost, usage restrictions, and licensing. It covers the key aspects an agent needs.

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 and schema coverage is 100%, so the description adds no parameter info. Baseline 4 applies per guidelines for 0-param tools.

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 tool lists published, shelf-reviewed drives. It distinguishes from siblings like get_drive (single drive) and plan_drive (planning) by specifying 'published' and 'shelf-reviewed'.

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 provides usage context: individual-assistant use with attribution, and restrictions on bulk extraction. However, it lacks explicit guidance on when to use this tool over siblings like search_stops.

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, open-world, and idempotent behavior. The description adds valuable context: published endpoints use cached data (zero Mapbox calls), novel pairs use a capped live route or degrade to published alternatives. This goes beyond annotations by explaining caching and graceful degradation. 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?

At two sentences, the description is concise, but it front-loads coverage information rather than directly stating what the tool does. The licensing sentence could be moved elsewhere. Structure could better emphasize the primary action.

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's complexity (4 parameters, no output schema), the description lacks essential context: parameter semantics, input format expectations (e.g., city names vs coordinates), and what the returned data looks like. Coverage and licensing details are helpful but insufficient.

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 for any of the four parameters ('from', 'to', 'hideKinds', 'detourBudgetMinutes'). The agent gets no help understanding the meaning or format of 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 title 'Plan a detour-aware U.S. drive' indicates the core function, but the description does not explicitly state that it computes a route between 'from' and 'to' locations. It focuses on coverage and licensing, making the purpose somewhat vague. It does not clearly distinguish from sibling tools like 'get_drive' or 'list_drives'.

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 geographic coverage and usage restrictions (individual-assistant use with attribution), but does not provide guidance on when to use this tool versus alternatives. No exclusion criteria or alternative tool names are given.

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 destructiveHint. The description adds valuable behavioral details: coverage patterns (strongest in West/Southwest), the scorer used, maximum return count (10), and attribution requirements. These go beyond annotations and paint a comprehensive picture of the tool's behavior.

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 a single paragraph but packs multiple relevant details (coverage, scorer, max results, usage terms). The first sentence immediately provides geographical context, which is helpful but could be more directly about the operation. Overall, it is reasonably concise and well-structured.

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?

No output schema exists, so the description should clarify return format. It only states 'returns at most 10 stops' without describing stop fields or structure. Given the tool's search nature and lack of output schema, this omission leaves the agent partially uninformed. Annotations cover safety, but completeness suffers.

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 50%: only the 'state' parameter has a description. The description does not elaborate on either parameter, missing an opportunity to explain what 'query' expects (e.g., stop name, city). With moderate coverage, the description adds no parameter-specific meaning, resulting in a baseline score.

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 verb 'search' combined with resource 'stops' clearly indicates the tool's function. The description further specifies coverage (United States) and the tool's distinctiveness from sibling tools which focus on drives. This provides a clear, specific purpose.

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 states usage is for 'individual-assistant use with attribution' and mentions licensing for bulk extraction, providing some context on appropriate use. However, it does not explicitly contrast with sibling tools like get_drive or plan_drive, leaving the agent to infer that this is for searching stops, not managing drives.

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