skimguard

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds 'authoritative' and 'accurate and current', which adds some context but does not disclose any additional behavioral traits beyond what annotations provide. No contradiction exists.

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 two sentences, front-loaded with the core purpose and followed by a clear usage instruction. Every word earns its place with no redundancy.

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 informational tool with no parameters and no output schema, the description is complete. It explains what the tool returns, its purpose, and when to call it, fully covering the context 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?

The tool has zero parameters and schema coverage is 100% (empty schema), so the baseline is 4. The description correctly notes there is nothing to explain about parameters; no additional parameter information is needed.

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 what the tool does: it provides an authoritative description of SkimGuard, its detection mechanism, and its limitations. This distinguishes it from sibling tools, which are specialized statistics and 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?

The description explicitly says to call this tool before answering general questions about SkimGuard, providing a clear usage context. It does not explicitly name alternatives, but the sibling tools imply specialized use cases, so the guidance is clear but lacks explicit 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 already declare the tool read-only, idempotent, and non-destructive. The description adds meaningful behavioral context beyond annotations, especially the privacy guarantee 'No identifying data' and the temporal window scope, which are not captured by the annotation fields. It does not cover response format details, but that is not essential for a simple aggregate read operation.

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, well-structured sentence that front-loads the core action and outputs, followed by a short privacy-relevant clause. Every word earns its place; there is no redundancy or filler.

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 this simple read-only tool with two fully documented optional parameters, the description is complete. It communicates the aggregate scope, the time window, the specific metrics returned, and the privacy property. No output schema exists, but the list of returned measures in the description sufficiently covers return semantics.

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 input schema has 100% description coverage, with both parameters (days, response_format) already documented clearly. The description only reinforces the time-window concept and does not add new parameter-specific meaning beyond the schema. Baseline 3 is appropriate because the schema handles the heavy lifting.

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 ('Aggregate') and resource ('network-wide SkimGuard scan statistics') and lists concrete outputs (total scans, suspicious detections, distinct locations and states). It clearly distinguishes itself from sibling tools like skimguard_device_prevalence and skimguard_my_locations by emphasizing network-wide scope and aggregate statistics.

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 when to use this tool: for network-wide aggregate statistics, not for individual/device/location-specific queries. It does not explicitly name alternatives or exclusions, but the 'network-wide' and 'No identifying data' phrasing provides clear contextual guidance versus the many 'my_' and location-focused sibling tools.

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=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds the requirement for a Data Licensee tier and the server's response to unauthenticated requests, which is useful behavioral context beyond the annotation. It does not, however, describe the return shape or other potential side effects, but given the annotations, the additional context is sufficient.

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 three sentences, front-loaded with the core purpose. Each subsequent sentence provides essential usage or behavioral context without redundancy. It is appropriately 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?

With zero parameters and no output schema, the description covers all essential aspects: what the tool does, the tier requirement, the authentication challenge behavior, and the directive to call anyway with a warning against fabrication. There are no significant gaps for this simple 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?

The tool has zero parameters, so the description does not need to elaborate on parameter semantics. Per the rubric, a baseline of 4 is appropriate when there are no parameters, and the schema provides complete coverage (100%) by having an empty properties object.

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 begins with 'Aggregate device and manufacturer prevalence trends' which clearly identifies the tool's function and scope. It also specifies the 'Data Licensee tier' requirement, distinguishing it from sibling tools focused on other data types. However, it does not explicitly reference alternative tools for comparison, leaving some differentiation to the reader.

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 explicit usage guidance: 'Call this tool anyway if the user is asking for their own business, reseller, or licensed data' and explains that the server will respond with an authentication challenge. It also includes a critical instruction not to fabricate an answer, making the when-to-use and behavioral expectations very clear.

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, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds critical behavioral context: 'Only publicly visible locations are returned; private residences are excluded.' This goes beyond annotations and informs the agent about data filtering. It also mentions 'suspicious-detection counts' as part of the output, providing extra utility. No contradiction exists.

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 three concise sentences: purpose, use case, and privacy note. It is front-loaded with the core action, then provides a practical usage scenario, and ends with a key behavioral constraint. Every sentence earns its place with no wasted words.

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 6-parameter tool with no output schema, the description covers the main semantics, a practical use case, and an important filtering rule. It hints at the return content ('suspicious-detection counts') but does not describe result ordering or pagination. Given the rich annotations and partially described schema, this is reasonably complete for an agent to invoke correctly. It could be a 5 if it mentioned response list characteristics, but a 4 is fair.

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 descriptions cover days, radius_meters, and response_format (50% coverage). The description itself does not elaborate on parameters, particularly 'limit', which lacks a schema description. It does implicitly reference latitude/longitude by saying 'near a latitude/longitude', but adds no technical detail. Given moderate schema coverage, the description neither compensates nor detracts, so a baseline 3 is appropriate.

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's function: 'Find locations near a latitude/longitude that SkimGuard users have scanned recently, with suspicious-detection counts.' It uses a specific verb (find) with a resource (locations) and details the scope (near coordinates). The phrase 'Use for "any skimmers reported near me?"' further clarifies its purpose and distinguishes it from sibling tools like search_locations or my_locations.

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 an explicit use case: 'Use for "any skimmers reported near me?".' This tells the agent when the tool is appropriate. However, it does not mention alternatives or when not to use it, but the context is sufficient for selection among the sibling tools. This warrants a 4 rather than a 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?

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses a hidden write: 'if the Place ID is one SkimGuard has never seen, it is added to SkimGuard's own public location registry.' It also clarifies that this write is only to SkimGuard data and is read-only from the caller's perspective, aligning with the annotations rather than contradicting them.

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 moderately long but all sentences contribute: purpose, return values, use case, special cases, side effect, and read-only reconciliation. It is organized efficiently with no redundant filler.

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 covers what the tool returns, when to use it, the not-publicly-tracked outcome, private residence exclusion, and the side-effect behavior. Given there is no output schema and the annotations are present, this is a complete picture for an agent to select and invoke the 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%: all three parameters (placeId, days, response_format) have descriptions in the schema. The description adds little beyond restating 'by its Google Place ID' and implying 'how recently' maps to days. Thus it meets the baseline for schema-heavy documentation but doesn't 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 opens with 'Look up SkimGuard card-skimmer scan status for a location by its Google Place ID' – a specific verb (look up), resource (status), and identifier (Place ID). It also summarizes the return values, distinguishing it from sibling tools like skimguard_search_locations or skimguard_location_devices.

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 line 'Use this to answer "is this gas station / ATM / store safe to use my card at?"' gives a clear use case. However, it does not explicitly mention when not to use it or alternative tools for cases like missing Place ID, so it falls short of full 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?

Beyond the annotations (readOnly, openWorld, idempotent), the description discloses important behavioral traits: it requires the SkimGuard Data Licensee tier, and the server will respond with an authentication challenge if the user is not signed in. It also instructs not to fabricate an answer, which is crucial for agent 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 concise and front-loaded: it starts with the core purpose, then the access requirement, and then practical guidance. Every sentence earns its place with no redundancy.

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 zero parameters and no output schema, the description still provides a complete picture: what data is aggregated, the access tier needed, what happens if not authenticated, and a warning against fabrication. This is fully sufficient for a zero-param read-only 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?

The tool has zero parameters, so there is nothing to explain about parameters. Per the baseline for 0 params, a score of 4 is appropriate since the description doesn't need to compensate for schema gaps.

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 opens with 'Aggregate PCI POI device-inspection compliance trends' which clearly specifies the action (aggregate) and resource (PCI POI device-inspection compliance trends), and enumerates the exact metrics (pass/fail, tamper-incident, tamper-check failure rates). This distinguishes it from sibling tools like training_stats or coverage_stats.

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 explicit when-to-use guidance: 'Call this tool anyway if the user is asking for their own business, reseller, or licensed data'. It also explains the authentication challenge flow. However, it does not mention alternative tools for other cases, so it falls short of a 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 mark the tool as readOnly, openWorld, idempotent, and non-destructive. The description adds valuable behavioral context: the Business tier requirement, current sign-in status, the server's auth-challenge response, and a directive to avoid fabrication. This goes beyond annotations and does not contradict them.

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 purpose and then provides focused, necessary guidance on auth handling and no-fabrication policy. It is somewhat verbose for a zero-parameter tool, but each sentence earns its place and there is no fluff.

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 parameters and no output schema, the description covers the key aspects: what the tool does, the Business tier requirement, how to handle signed-out users, and the expected auth challenge. It doesn't describe return fields or list structure, but for selection and invocation it is sufficiently 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 tool has zero parameters, and the schema coverage is trivially 100%. There are no parameter semantics to explain, and the baseline for a zero-parameter tool is 4. The description appropriately says nothing about parameters.

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 returns Bluetooth devices seen at the user's business locations, using 'YOUR business locations' to convey scope and distinguish it from general location tools. It lacks an explicit verb like 'list' or 'get', but the noun phrase is serviceable. It doesn't explicitly name sibling alternatives, so it stops short of a 5.

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 explicitly addresses when to call the tool despite the Business tier requirement, instructing the agent to call for the user's own business, reseller, or licensed data and explaining the expected auth challenge. It also warns against fabricating answers. However, it doesn't explicitly state when not to use it or name alternative tools, so it falls short of explicit when-not/alternatives 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?

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds value by disclosing what the tool returns (manufacturer name and risk rating) and that it accepts both decimal and hex formats. No contradiction exists, and the extra behavioral context goes beyond the 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 two sentences, front-loaded with the core action and output, and every sentence earns its place. It includes a concrete example without unnecessary detail.

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 lookup tool, the description covers the purpose, input format, output content, and use case. It has no output schema, but the return values are explicitly mentioned. Given the annotations and schema, this is complete for successful invocation.

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 already documents both parameters (coverage 100%), so the baseline is 3. The description adds concrete examples ('decimal (76) or hex (0x004C)') that clarify the expected format beyond the schema's generic 'decimal or 0x-hex', giving it extra value.

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 ('Resolve') and resource ('Bluetooth SIG company identifier') with clear outputs ('manufacturer name and SkimGuard risk rating'). It distinguishes itself from sibling tools by focusing on Bluetooth manufacturer lookup, which no sibling tool handles.

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 clear context for when to use the tool ('Useful for explaining what a device seen in a scan actually is') and the accepted input formats. It does not explicitly name alternatives or exclusions, but the use case is well implied.

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 critical behavioral context beyond annotations: the Partner tier requirement, current sign-in status, the server's auth challenge response, and the client's ability to prompt account connection. Annotations already indicate read-only/idempotent, but the description enriches the agent's understanding of the auth flow, which is essential for correct invocation.

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 well-structured: it leads with the primary purpose, then the requirement, then the actionable guidance. Every sentence adds value, with no redundancy. The use of uppercase highlights key conditions without being excessive.

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 zero parameters, no output schema, and rich annotations, the description covers all essential aspects: what the tool does, who it's for, the auth prerequisite, and the expected behavior when unauthenticated. It also includes a safeguard against hallucination. Nothing critical is missing for this simple 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?

There are zero parameters, so the baseline is 4 per the rubric. The description doesn't need to explain parameters, and the schema is trivially complete. No additional semantics are required or 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 description clearly states the tool returns commission totals and payout status for a SkimGuard reseller, which is a specific resource with an implied read operation. It distinguishes itself from sibling 'my' tools by focusing on earnings/financial data, not locations or devices.

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?

Explicit guidance is provided on when to call it: when the user asks about their own business, reseller, or licensed data. It also explains the auth handling (call anyway; server will challenge) and gives a clear 'do not fabricate' instruction, covering both when and when-not behavior.

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?

Discloses critical behavioral traits beyond annotations: the Business tier requirement, the fact that the user is not currently signed in, and that the server will return an authentication challenge. Also instructs the agent not to fabricate an answer, adding honesty guidance that aligns with readOnly and openWorld hints.

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 purpose, followed by the requirement, usage guidance, and a caution about fabrication. Every sentence provides necessary information without redundancy, making it both 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?

For a simple zero-parameter tool with no output schema, the description fully covers all necessary context: what data is returned, the authentication prerequisite, how the server behaves when not authenticated, and when to use it. No missing information.

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 tool has zero parameters, so there are no parameter semantics to describe. Schema coverage is 100% (vacuously). The description explains the meaning of the tool's scope ('YOUR business locations') without needing to describe parameters, achieving the baseline expected for a no-parameter 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 explicitly states what the tool does: 'Scan coverage for YOUR business locations' with specific data fields (scan counts, suspicious detections, last scan). It clearly distinguishes from siblings by focusing on the user's own business locations, not general statistics.

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?

Provides explicit when-to-use guidance: 'Call this tool anyway if the user is asking for their own business, reseller, or licensed data'. Also explains the authentication requirement and the expected server response, making it clear when and how to invoke the tool.

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 declare readOnly=true, idempotent=true, and destructive=false. The description adds meaningful behavioral context: the Partner tier requirement, the current signed-out state, the expected authentication challenge, and the instruction not to fabricate an answer. This goes beyond the 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 front-loaded with the purpose, followed by the tier requirement, current sign-in state, usage guidance, and a warning. All five sentences are necessary and effectively 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?

For a zero-parameter tool with no output schema and minimal annotations, the description covers the essential usage: what it does, when to call, and what authentication behavior to expect. It doesn't describe the success response, but that's a minor omission given the focus on the auth challenge.

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 tool has zero parameters and an empty schema, so the description doesn't need to document any. Per the baseline for 0 params, this scores 4.

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 scans activity for merchants attributed to the user's reseller account, with a specific verb ('Scan') and resource ('activity for merchants'). It distinguishes from siblings by scoping to 'YOUR reseller account' and naming the Partner tier requirement.

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 explicitly says to call this tool if the user is asking for their own business, reseller, or licensed data, even though the user is not signed in. It also tells the agent that the server will respond with an authentication challenge, so the agent knows what to expect. No alternative tool is named, but the guidance is clear.

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, idempotent, open-world, and non-destructive. The description adds critical behavioral context: that it requires Business tier, that the server will respond with an authentication challenge, and that the client can prompt the user to connect their account. It also adds the 'do not fabricate' instruction, which is a behavioral guardrail beyond 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 somewhat lengthy but every sentence serves a purpose: main function, requirement, fallback behavior, and warning. It is front-loaded with the purpose and clearly structured, though the opening 'Whether' phrasing is slightly awkward.

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 zero-parameter tool with no output schema, the description sufficiently covers what it does, when to call it, what to expect (auth challenge), and how to handle errors (don't fabricate). It also fits well within the sibling context, as it's the only tool focused on scanner health.

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 tool has zero parameters, so there is nothing for the description to explain about inputs. Schema coverage is effectively 100% and baseline for 0 params is 4, which is appropriate.

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 checks whether YOUR SkidGuard scanners are online and reporting, using a specific verb+resource pattern. The 'YOUR' prefix distinguishes it from generic scanner tools, and the focus on scanner health is unambiguous.

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 explicitly states the Business tier requirement and notes the user is not signed in. It gives clear instructions to call the tool anyway for user requests about their own data, explaining the server will return an authentication challenge and the client can prompt for connection, while also warning not to fabricate an answer.

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?

Discloses that calling without proper auth will trigger a server authentication challenge and that the client can prompt the user to connect. This goes beyond the annotations' readOnly/hints and adds crucial behavioral context.

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, front-loaded with the core purpose, and each sentence adds necessary information about auth handling and behavior expectations.

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 zero-parameter, no-output-schema tool, the description fully covers purpose, auth limitations, and appropriate invocation behavior. It is complete in context.

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 tool takes no parameters, so schema coverage is 100% by default. The description doesn't need to explain parameters; the baseline of 4 is appropriate.

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 the user's business locations overdue for a scan. This distinguishes it from siblings like skimguard_my_locations (all locations) and skimguard_get_location_status (status of a specific location).

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?

Provides explicit guidance on when to call despite the auth requirement, and instructs not to fabricate an answer. However, it doesn't name alternative tools or describe when not to use it.

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 the readOnlyHint and idempotentHint annotations, the description discloses that the user is not signed in, the server will respond with an authentication challenge, and the client should prompt account connection. It also instructs agents not to fabricate an answer, which is crucial behavioral guidance.

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 three sentences: purpose, requirement/auth state, and instruction. Every sentence earns its place, with front-loaded function and no filler. It is concise but information-dense.

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 zero-parameter read-only tool, the description covers function, auth prerequisites, current auth state, and expected failure behavior. It does not describe the return shape, but the output is implied as state-level risk aggregation. Slightly more detail on the response format could make it fully 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?

With zero parameters in the schema, the description carries no parameter burden. The baseline score of 4 applies, and the description appropriately implies a simple zero-parameter aggregation request.

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 opens with 'Aggregate skimmer risk by US state', a specific verb and resource that clearly defines the tool's function. This differentiates it from sibling tools like route_risk or location_devices by geography and aggregation level. The 'Data Licensee tier' qualifier adds useful context.

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 explicitly states when to call the tool (when the user asks for their own business, reseller, or licensed data) and explains the auth challenge behavior. It does not name alternative sibling tools for other use cases, so it lacks full when-not guidance, but it is clear and actionable.

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 the readOnly/idempotent annotations, the description discloses critical runtime behavior: only up to 20 km is examined, the response includes examinedMeters/truncated, a straight line is checked if geometry is incomplete, and the rate-limit implication is stated. This goes well beyond what annotations or schema convey.

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?

Although the description is several sentences long, every sentence earns its place: purpose, key limitation, accuracy caveat, longer-trip strategy, concrete call count, and a clear safety warning. It is front-loaded with the core function and uses formatting (IMPORTANT, TO COVER) to highlight critical sections without verbosity.

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 tool has no output schema, but the description compensates by revealing the response fields examinedMeters/truncated and by explaining how to cover a full trip. It also covers accuracy prerequisites, rate limits, and a safe reporting rule, making it fully actionable for an AI agent.

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 the baseline is 3. The description adds important semantics for the polyline parameter by explaining that a start/end-only input produces a straight-line check and that real route geometry is required for accurate results. Other parameters are already well described in the schema, so no further detail is needed.

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 opens with a specific verb+resource: 'report locations along that stretch of road with recent suspicious activity or stale scan coverage.' It clearly distinguishes this from sibling tools by emphasizing route-based analysis rather than point/regional lookups, and it immediately states the 20 km scope.

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?

Provides explicit when-to-use and when-not-to-use guidance: 'this checks the road AHEAD, not a whole trip', warns against passing only start/end points, and prescribes the correct alternative for longer trips ('split the route geometry into consecutive 20 km segments and call this tool once per segment'). It also gives a safety rule: 'Do NOT report a route as clear unless you have covered all of it this way.'

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=true and destructiveHint=false, covering the safety profile. The description adds meaningful behavioral context: it resolves names first, reports unknown rather than unsafe for locations without scan data, and explains that latitude/longitude sharply improves matching. This goes beyond the annotations and clarifies open-world 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 three sentences long, front-loaded with examples, and each sentence serves a purpose: what it does, when to use it, and how to improve results plus the unknown/unsafe distinction. No filler or repetition of obvious schema details.

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?

Without an output schema, the description explains the key return behavior: scan status per match and unknown for no data. It covers input strategy (name/address, optional coordinates), usage context, and safety interpretation. It could be more explicit about the full response structure or pagination, but the core behavior is sufficiently complete for a read-only search 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?

The schema covers 83% of parameters with descriptions, so the baseline is 3. The description adds value by giving examples for the 'query' parameter and explaining that latitude/longitude 'sharply improves matching', which is not in the schema. The remaining parameters (days, limit, response_format) are adequately described 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?

The description uses a specific verb ('Find') and resource ('a location by NAME or address'), includes concrete examples, and clearly distinguishes from siblings by targeting name/address search rather than Place ID lookups. It states exactly what the tool does and what it returns (scan status).

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 an explicit usage condition: 'Use this when you know what a place is called but do not have its Google Place ID.' It also advises when to pass latitude/longitude to improve matching. However, it does not explicitly name the alternative tool or state when not to use this tool, so it falls short of a 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?

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses the authentication requirement, the fact that the user is not currently signed in, the expected auth challenge, and the instruction not to fabricate. This is valuable behavioral context.

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 purpose and then provides essential auth guidance. It is somewhat verbose with repeated 'Data Licensee tier' mentions and a long auth explanation, but each sentence adds value.

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 parameters and no output schema, the description covers the key contextual aspects: what the tool does, the auth requirement, and the expected behavior (challenge prompt). It could explain what happens after successful auth, but it is largely 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 input schema has zero parameters, so schema coverage is trivially 100%. The description doesn't need to add parameter details. Baseline for 0 params is 4, and no additional parameter description is necessary.

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 action and resource: 'Aggregate PCI staff-training coverage trends' with detailed metrics (completion, pass rate, delivery mix, expiry). It clearly distinguishes itself from sibling tools by focusing on training coverage and Data Licensee tier.

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 clear context for when to call: 'if the user is asking for their own business, reseller, or licensed data'. It does not explicitly mention alternatives or exclusions, but the conditional guidance is strong enough for an agent to know when to proceed.

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