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

With no annotations, the description carries the burden. It mentions the API endpoint, default limit, and pagination offset, which hint at behavior. However, it does not disclose authentication needs, rate limits, or broader side effects (e.g., whether this is read-only). The word 'List' implies non-mutating, but that is implicit.

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 organized with a purpose line, API endpoint, and a list of args. It is front-loaded with the core purpose. It is longer than a simple two-liner but every line is informative. The structured arg list is easy to scan, though it could be slightly more concise if trimmed.

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 purpose, endpoint, and all parameter semantics comprehensively. An output schema exists, so return values need no explanation. Missing pieces are explicit exclusions or caveats (e.g., 'not for DNS events') and any error/edge-case behavior. Overall it is complete for a list operation.

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%, so the description must compensate. It does so thoroughly: from_ and to are explained with accepted formats (epoch ms, ISO-8601, relative offsets), limit has a default, offset is explained as pagination, ampdisposition has an example, sha256 is described, and timezone is defined. This adds significant meaning beyond the bare 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 'List AMP (Advanced Malware Protection) retrospective activity events' and explains what that means ('files that were re-classified as malicious after they were first seen'). This is a specific verb+resource+scope that distinguishes it from sibling activity tools like DNS, proxy, and firewall.

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 context is clear: this tool is for AMP retrospective events, which implies when to use it. However, it does not explicitly mention alternatives or exclusions relative to sibling activity tools. The description provides enough context for a basic selection decision, but lacks an explicit 'use this when' statement.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It correctly implies a read operation via 'List' and includes details on pagination (limit, offset), but it does not disclose potential side effects, rate limits, or authentication requirements. The API endpoint is provided, adding some transparency.

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 well-structured as a docstring with a one-line summary, followed by the API endpoint and a formatted list of arguments. Every parameter earns its place, and the content is front-loaded with the core purpose. It is appropriately concise for a tool with 10 parameters.

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 (10 parameters, output schema present), the description is nearly complete. It covers all parameters, clarifies required fields, and notes timezone handling. It does not explain the response structure, but the output schema likely covers that. Minor gap: no mention of error handling or boundary behaviors.

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 are absent (0% coverage), so the description fully compensates by explaining each parameter's format and purpose. It clarifies time formats, defaults (limit 100), and filter types (domains, categories, verdict, etc.), providing clear semantics beyond 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 opens with 'List DNS activity events,' which is a specific verb and resource that clearly identifies the tool's purpose. The name and API endpoint further specify DNS activity, distinguishing it from sibling tools like proxy, firewall, and AMP retrospective activity.

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 implies usage for DNS activity events, but it does not explicitly state when to choose this tool over the sibling activity tools (e.g., proxy, firewall). No alternative tools are mentioned, so the guidance is implied rather than explicit.

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?

With no annotations, the description carries the full burden. It discloses the API method (GET) and the required time-range parameters, but does not explicitly state safety (e.g., read-only) or discuss behaviors like pagination limits, result ordering, or rate limits. The 'List' verb and GET API imply a non-destructive operation, but this is not spelled out.

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 opens with a one-line purpose, gives the API endpoint, and then lists parameters in a readable format. Every sentence adds value; there is no fluff or 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?

The description covers all parameters, required fields, and accepted formats, and an output schema exists so return values need no explanation. It could also mention explicit when-to-use vs. sibling tools, but that falls more under usage guidelines. Overall, it is sufficiently complete for a list operation with good parameter coverage.

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 0% description coverage, so the description is the only source of parameter meaning. It provides detailed semantics for every parameter: accepted time formats for from_/to, default for limit, offset as pagination, and definitions for each filter (identityids, ruleid, verdict, categories, timezone). This fully compensates for the schema's lack of descriptions.

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 'List network firewall activity events,' which uses a specific verb and resource. It clearly distinguishes itself from sibling tools like get_activity_dns and get_activity_proxy by specifying 'firewall.'

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 implies that this tool is for firewall activity events, but it does not explicitly state when to use it over the sibling activity tools or mention any exclusions. The usage context is clear enough from the name and first line, but no alternatives or when-not-to-use guidance is provided.

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?

No annotations are provided, so the description carries the burden. It discloses the HTTP method (GET) and details about timezone handling and pagination, which is useful. However, it does not explicitly state that this is a read-only operation, mention authentication requirements, or describe error behavior, leaving some gaps.

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 well-structured docstring with the API endpoint followed by an Args list. Each parameter gets a single concise line, and the content is front-loaded with the core action. 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?

Despite having 12 parameters and no schema descriptions, the description covers every parameter, the API endpoint, and special formatting details for time fields and timezone. An output schema exists, so return values are presumably covered there. It is complete for a reporting tool of this complexity.

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%, so the description fully compensates by explaining every parameter, including accepted formats for from_/to (epoch, ISO-8601, relative offsets), default values, and filter semantics with examples (e.g., verdict 'allowed' or 'blocked'). This adds substantial meaning beyond the raw 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 'List proxy (Secure Web Gateway) activity events', providing a specific verb and resource. The term 'proxy' differentiates it from sibling tools that focus on DNS, firewall, or AMP activities.

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 gives no explicit guidance on when to use this tool versus alternatives like DNS or firewall activity tools. While the name and description imply proxy/SWG reporting, there are no when-to-use or when-not-to-use statements, and no alternatives are mentioned.

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?

Since no annotations are provided, the description carries the full burden. It discloses the HTTP method (GET), the fact that it returns a single object, and the summary contents, which are meaningful behavioral traits. It does not mention authentication, errors, or rate limits, but for a simple read-only report call with no parameters, the added context is strong.

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: a single main sentence with a parenthetical list, a clarifying sentence about the return type, and an API reference. Every line adds value, with no redundant or filler text.

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 is complete: it states the purpose, the return value's scope, the single-object semantics, and provides the exact API endpoint. The output schema covers detailed return values, so the description need not repeat them, and the simplicity of the tool means no additional context is required.

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 no properties, so the baseline is 4. The description does not need to explain parameters because there are none; it appropriately focuses on the output and semantics.

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 identifies the tool as retrieving 'this Umbrella Managed Provider console's subscription/usage summary' and enumerates the specific fields (package name, seats, customer count, status, dates). The phrase 'Not a list — returns a single object' explicitly differentiates it from the sibling list tools, meeting the requirement for a specific verb+resource and sibling distinction.

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: it is for obtaining the console's subscription/usage summary and emphasizes that it returns a single object rather than a list, which helps choose it over list-oriented siblings. However, it does not explicitly name alternative tools or state when not to use it, so it falls slightly 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?

No annotations are provided, so the description carries full burden. It includes the GET API endpoint, implying read-only, but fails to disclose pagination behavior, return format, permissions, rate limits, or other behavioral traits. The description stays at the surface level without revealing operational details.

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: a clear purpose statement, the API endpoint, and an Args section with parameter details. Each line earns its place, with no filler, and the format is easily scannable.

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 an output schema present, return values need not be explained. The description covers the core function and parameters, making it minimally viable for a simple list operation. However, it lacks any usage context, behavioral detail, or operational constraints, leaving gaps in full 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?

The description adds valuable parameter semantics: 'limit: Max results per page (1-100)' and 'offset: Pagination offset.' This goes beyond the schema, which has 0% description coverage and only provides types and defaults. The range and purpose of parameters are clarified.

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 'List application categories (App Discovery).' with a specific verb and resource, and also provides the API endpoint for added clarity. However, it does not explicitly differentiate from sibling tools like 'cisco_umbrella_list_applications', though the resource name is distinct enough to infer.

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 is given about when to use this tool versus alternatives such as 'cisco_umbrella_list_applications' or other list tools. There is no context on use cases, prerequisites, or when not to use it, so the usage guidance is absent.

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?

With no annotations, the description carries the full burden for behavioral disclosure. It only states 'List' and lists parameters, but does not describe pagination behavior (e.g., default limit, max results), response structure, or any side effects beyond it being a 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 well-structured with a one-line summary, API endpoint, and a clear list of args. It is concise and free of extraneous information, though the API line is somewhat redundant with the tool name.

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 list operation with an output schema, the description covers all parameters and the core purpose, but lacks usage guidance and behavioral details like pagination defaults. The output schema presumably covers return values, so the description is reasonably 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?

All eight parameters are described with meaningful detail beyond the schema, including value formats (comma-separated, boolean), examples (sources: 'dns,swg,cdfw'), and semantics (limit as max results per page). Since schema coverage is 0%, this description fully compensates.

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 'List discovered cloud applications (App Discovery).' with a clear verb and resource, and includes the API endpoint. This clearly distinguishes it from sibling tools like list_application_categories or get_activity_*.

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 no guidance on when to use this tool versus alternatives such as activity reporting or category listing. There is no mention of prerequisites, exclusions, or 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?

No annotations are provided, so the description carries the burden. The 'List' verb and 'GET' API endpoint indicate a read-only operation, and the max limit of 100 is disclosed. However, it does not mention authentication requirements, rate limits, or behavior beyond pagination, leaving some transparency gaps.

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 extremely concise and well-structured: purpose in the first line, API endpoint for reference, then a clear args list. Every sentence provides value without 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?

Given the tool's simplicity, an output schema exists (so return values are covered), the description adequately covers purpose, scope, endpoint, and parameters. It lacks explicit guidance on when to prefer this tool over siblings, but it is otherwise complete for a straightforward list operation.

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 0% schema description coverage, the description fully compensates by explaining both parameters: page is the page number (default 1), and limit is max results per page (default 100, max 100). It adds the max constraint not present 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 clearly states the tool lists customer organizations under the MSP account, using a specific verb ('List') and resource ('customer organizations'). It distinguishes itself from sibling tools that list other entities like roaming computers, applications, or protocols.

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 that this is for the Umbrella Managed Provider (MSP) account, implying it should be used when the agent needs to see managed customer organizations. It does not explicitly mention when not to use it or name alternatives, but the MSP-specific scope differentiates it from sibling list 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?

With no annotations, the description carries the transparency burden. It discloses the HTTP method (GET) and the endpoint, implying read-only, and documents each parameter's meaning. However, it does not address pagination behavior limits, authentication, or other operational caveats, leaving some gaps.

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 compact and front-loaded with the core purpose, followed by the API endpoint and a structured Args list. No redundant sentences; every element serves a purpose.

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 an output schema, so return values are covered. The description explains all parameters and the endpoint. It lacks explicit cross-tool guidance, but overall it is sufficiently complete for a straightforward list operation.

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 0%, so the description must compensate. It does so thoroughly via an Args section that explains identity filtering, pagination, sort fields, and order values, adding substantial meaning beyond the bare 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 opens with 'List discovered network protocols (App Discovery),' providing a specific verb, resource, and context. This clearly distinguishes it from sibling tools like list_applications and list_application_categories by focusing on protocols.

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 identifies the App Discovery domain but does not explicitly explain when to choose this over list_applications or list_application_categories. Usage is implied by the tool name and resource, but no exclusions or alternatives are mentioned.

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 discloses the HTTP method (GET), pagination via page and limit, and filter semantics. However, in the absence of annotations, it does not explicitly state read-only nature, authentication needs, or behavior like how filters combine. Some behavioral traits are covered, but not all.

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 well-structured and front-loaded: purpose first, then API endpoint, then a clear list of arguments. Every sentence contributes useful information without redundancy or fluff. The layout is scannable and efficient.

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 the main purpose, endpoint, all parameters, and pagination. Since an output schema exists, the absence of response format details is acceptable. It could go further by specifying allowed filter values and date/time formats, but overall it is complete enough for a list 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?

Given schema description coverage is 0%, the description compensates by explaining each of the 7 parameters with meaningful details: defaults, max limit, partial matches for name, and the semantics of last_sync_before/after. It lacks allowed values for status and date formats, but provides substantial value beyond the bare 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 starts with a specific verb 'List' and resource 'roaming computers', and clarifies in parentheses that these are endpoints running the Umbrella roaming client. This clearly distinguishes it from sibling tools like activity or application list 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 makes the tool's purpose clear but does not explicitly state when to use it versus alternatives or mention exclusions. Sibling tools are quite different, so usage is implied, but no direct guidance or alternative routing is provided.

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