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

No annotations are provided, so the description carries the full burden. It accurately describes a read operation (getting endpoints and metrics) with no side effects mentioned. It does not discuss permissions or rate limits, but for a simple read tool, the description is adequate.

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 purpose and includes a helpful note about reuse. The Args section is somewhat verbose but adds necessary detail. Overall, it's concise enough without missing key information.

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 that an output schema exists (not shown), the description does not need to detail return values. It covers the tool's purpose, parameters, and usage context well, though it could mention what the aggregated metrics look like or any pagination.

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%, but the description explains all three parameters (app_id, from_, to) in detail, adding meaning beyond the schema titles. It specifies that from_ and to are ISO 8601 datetimes.

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 gets all endpoints for an application and also aggregated performance metrics. This distinguishes it from siblings like get_app_endpoint_traces (traces) and get_app_metrics (metrics only).

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 hints at when to use the tool (identifying high throughput, latency, error rate) and mentions endpoints can be used in other tools. However, it does not explicitly state when not to use or compare against alternatives like get_app_endpoint_traces.

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. The description only states the basic action without disclosing behavioral traits such as read-only nature, rate limits, data freshness, or response structure. This leaves significant gaps for agent decision-making.

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: one sentence plus an Args block. The main sentence is front-loaded. The Args block, while somewhat redundant with the schema, aids quick comprehension.

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 available, the description need not explain return values. However, it lacks usage nuance (e.g., time range limits, result set size). The 4 required parameters are fully listed, but the description does not set expectations for what constitutes 'recent' or how results are ordered.

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%, but the description includes an Args section that adds type and brief descriptions for each parameter (e.g., 'The ID of the Scout APM application'). This compensates for the schema's lack of descriptions, though it does not cover all details like allowable formats.

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 retrieves recent traces filtered by app and endpoint, using specific verbs and resource names. It implicitly distinguishes from siblings like get_app_trace (singular) and get_app_error_groups.

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 explicit guidance on when to use this tool versus alternatives (e.g., get_app_trace for a single trace). Usage is implied from the description but not stated.

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 must carry the full burden. It does not disclose important behavioral traits such as: whether the tool requires specific authentication, pagination behavior, or what happens if date range parameters are omitted (they are required but not explained). The missing from_ and to parameters are critical for safe usage.

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 short but includes a redundant Args list that duplicates schema info without adding value. It fails to mention key parameters (from_, to), indicating poor scoping. Conciseness is undermined by incompleteness.

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 presence of an output schema, the description does not need to explain return values. However, it still fails to document all input parameters (missing from_, to) and does not account for the conflict between 'recent' and required date ranges. Essential context is absent.

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 add meaning. It lists three parameters (app_id, endpoint_id, error_group_id) but neglects the two required parameters from_ and to. While it clarifies optional filters, the omission of vital time range parameters severely limits its usefulness.

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 identifies the action (get) and resource (error_groups for an app), and mentions optional filters. However, it omits the required date range parameters (from_, to) present in the schema, which are essential to understand the scope of data returned. The phrase 'recent' conflicts with the explicit time range parameters, reducing clarity.

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 provided on when to use this tool versus its siblings (e.g., get_app_endpoint_traces, get_app_trace). There is no mention of appropriate contexts, prerequisites, or alternatives. The description is purely functional with no usage strategy.

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 must cover behavioral traits. It mentions caching (5 minutes) and the ability to filter by insight_type, but does not disclose read-only nature, authentication needs, rate limits, or error behavior for invalid app_id.

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 brief overview, a list of insight types, and a docstring-style parameter section. It is concise yet informative, though some sentences could be slightly tighter.

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 existence of an output schema (not shown), the description does not need to detail return values. It covers caching, filtering, and parameter details adequately. Missing information about pagination or error handling prevents a higher score.

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?

Input schema has 0% description coverage, so the description must compensate. It clearly explains each parameter: app_id as the application ID, insight_type with allowed values (n_plus_one, memory_bloat, slow_query) and default, and limit as max items per type with default 20. This adds essential meaning 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 clearly states that the tool retrieves or generates performance insights for an application, listing specific types like N+1 queries, memory bloat, and slow queries. It distinguishes itself from sibling tools (e.g., get_app_endpoints, get_app_metrics) by focusing on application-level performance insights.

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 getting performance insights but does not provide explicit when-to-use or when-not-to-use guidance relative to siblings. No exclusions or alternatives are mentioned, leaving the agent to infer context.

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 full burden. It clearly describes the tool as a read operation returning job details and metrics, but it doesn't explicitly state it is read-only or mention behavior on invalid dates. The field list adds 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 concise and well-structured: a brief purpose and use case, a list of returned fields, and a clear parameter list. No unnecessary information.

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 an output schema, the description lists key fields. It covers purpose, parameters, return content, and a use case. For a simple listing tool, it is complete and informative.

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, but the description fully explains each parameter: app_id is the application ID, from_ and to are start/end datetimes in ISO 8601 format. This adds essential meaning 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 clearly states it gets all background jobs for a specific application and also aggregated performance metrics. It names specific fields and use case, making the tool's purpose unambiguous and distinct from siblings like get_app_job_traces.

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 explains the tool is useful for identifying high throughput, latency, or error rate jobs with a single call, providing clear usage context. However, it does not explicitly mention when not to use it or compare to alternatives like get_app_job_traces.

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 must disclose behavioral traits. It states traces are 'recent' and filtered to a job, but does not clarify recency bounds, pagination, response limits, or error states. Listing trace fields adds some value but edges are missing.

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 purpose sentence, trace field list, and parameter docs. It is front-loaded and efficient, though the 'Each trace includes' line could be integrated with output schema info.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 required parameters, no annotations, and an output schema, the description provides adequate parameter semantics but misses overall context like usage scenarios, pagination, or error handling. It is sufficient but not 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?

Schema description coverage is 0%, so the description fully documents each parameter: app_id ('ID of the Scout APM application'), job_id ('Base64-encoded job ID'), from_ and to (ISO 8601 datetime). This adds meaning beyond schema names.

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 'Get recent traces for an app filtered to a specific background job,' specifying the verb (get), resource (traces), and scope (app and job). This distinguishes it from siblings like get_app_trace (single trace) and get_app_jobs (list jobs).

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 lacks guidance on when to use this tool versus alternatives. No mention of prerequisites, fallbacks, or context like 'use for debugging job performance' or 'for a single trace use get_app_trace instead.'

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 were provided, and the description does not disclose behavioral traits such as required permissions, rate limits, or what happens if the metric is unavailable. For a tool with no annotations, this is insufficient.

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 verbose, using a Python docstring style with parameter listings. It could be more concise, but the information is well-structured and front-loaded.

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. However, it lacks context on prerequisites, authentication, or limitations. Given the complexity and sibling tools, this description is minimally adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 0%, the description adds significant meaning by explaining each parameter: app_id, metric, from_, and to. It specifies that from_ and to should be in ISO 8601 format, which is valuable 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 clearly states 'Get individual metric data for a specific application,' specifying both the action and resource. It effectively distinguishes from sibling tools like get_app_endpoints and get_app_insights by focusing on metric data.

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 does not explicitly guide when to use this tool versus alternatives like get_endpoint_metrics or get_job_metrics. The purpose is implied but lacks explicit when-to-use or when-not-to-use instructions.

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 must fully convey behavior, but it only states the operation is a retrieval. It does not disclose any potential side effects, authentication requirements, rate limits, or data volume implications, leaving significant 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 concise with a clear structure: purpose sentence followed by parameter list. However, the parameter list could be more compact, and the overall length is appropriate without excess.

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?

While the output schema exists (so return values don't need explanation), the description lacks context about trace semantics, error handling, or data completeness. For a simple retrieval, it is minimally adequate but leaves room for improvement.

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 includes 'Args' that briefly explain each parameter (app_id and trace_id as IDs), adding meaning beyond the schema's minimal titles and types. This compensates for the schema's low description coverage.

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 action ('Get') and the resource ('individual trace with all spans'), making the purpose immediately understandable. It distinguishes from sibling tools like 'get_app_endpoint_traces' by focusing on general traces.

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 no guidance on when to use this tool versus alternatives. There is no mention of context, prerequisites, or exclusions, leaving the agent to infer usage through the tool name and parameters alone.

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 burden of behavioral disclosure. It implies a read operation but does not mention auth, rate limits, return format, or any edge cases. The description is silent on most behavioral traits.

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 with a clear header and a structured list. No extraneous text. However, the parameter list could be integrated more naturally, and the description is slightly terse.

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 and presence of an output schema, the description adequately covers the main action. However, it lacks details about time range constraints, data granularity, or empty result handling.

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 meaningful explanations for all 5 parameters (e.g., 'The ID of the Scout APM application.'), which goes beyond the schema's bare titles. This compensates for the low schema description coverage.

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 retrieves a single timeseries metric for a specific endpoint, using a specific verb and resource. It does not explicitly differentiate from sibling tools like get_app_metrics, but the specificity reduces ambiguity.

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 provided on when to use this tool versus alternatives (e.g., get_app_metrics for multiple metrics). There are no conditionals or exclusions 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?

No annotations provided, so the description must disclose behaviors. It only states it retrieves a single timeseries metric but does not mention authorization needs, rate limits, error handling, or what happens if the job is missing. The return format is also not described despite an output schema existing.

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 with a clear first sentence and a brief list of valid metrics. The Args block is slightly verbose but acceptable given the lack of schema descriptions. No unnecessary sentences.

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 5 required parameters and an output schema, the description covers the purpose and parameters adequately. However, it omits details about the output format (e.g., data points or single value) and error scenarios, leaving gaps for a data-retrieval 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 0%, so the description adds value by listing and describing each parameter (app_id, job_id, metric, from_, to) and providing valid metric values. However, from_ and to lack format details beyond 'ISO 8601'. Overall, it compensates partially for the missing schema 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 clearly states 'Get a single timeseries metric for a specific background job', specifying the verb and resource. It lists valid metrics, distinguishing it from sibling tools like get_app_jobs (list jobs) and get_app_job_traces (traces).

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 when to use (when a specific job's metric is needed) but lacks explicit when-not-to-use or alternatives. No mention of when to choose this over get_app_metrics or other siblings.

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. The description implies a read-only operation by retrieving instructions, with no mention of side effects or destructive actions. It could benefit from explicitly stating it does not modify any state, but the behavior is transparent enough for an instruction-gathering tool.

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 clear purpose statement, usage instruction, supported frameworks list, and parameter details. It is concise without unnecessary information. The supported frameworks list adds some length but is relevant.

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 presence of an output schema (not shown), the description does not need to detail return values. It mentions 'Complete setup instructions including installation, configuration, and examples.' Overall, it provides sufficient context for the tool's function and usage.

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 a single 'framework' parameter with 0% coverage (no description). The description compensates by listing supported frameworks and giving an example ('fastapi', 'django', 'celery'), adding context that the schema lacks. It could be improved by providing a full list of accepted values.

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 provides step-by-step setup instructions for Scout APM in a framework. It distinguishes from sibling tools that retrieve app data, not configuration instructions. The verb 'Get' and resource 'setup instructions' are specific.

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 advises 'Always use this tool first when asked to setup/instrument/configure Scout APM in an application.' It provides a list of supported frameworks, aiding tool selection. While it doesn't mention when not to use it or alternatives, the guidance is clear for its intended use case.

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 fully bears the transparency burden. It explicitly states this is a read operation and details the returned fields, including conditional fields like 'with limit if applicable'. No side effects or auth needs are mentioned, but for a simple get tool this is acceptable.

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 consists of two clearly worded sentences with no unnecessary information. It front-loads the core purpose and then lists the returned data.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and an output schema exists, the description sufficiently explains what the tool returns. It covers all mentioned data categories and is complete for the tool's simplicity.

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 schema coverage is 100%. The description does not need to add parameter meaning, and the baseline for 0-parameter tools is 4. No extra 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 the tool retrieves usage and billing data for the current billing period. It lists specific data points returned, distinguishing it from sibling tools that focus on app-specific metrics.

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 retrieving billing information but provides no explicit when-to-use or when-not-to-use guidelines, nor does it reference alternatives among siblings.

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 discloses the filtering capability and default period, but does not mention any side effects. Since it's a read-only listing tool, the transparency is adequate.

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 with three sentences and an explicit 'Args' block. It is well-structured and front-loaded with the core 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?

With only one optional parameter and an output schema present, the description provides sufficient context: purpose, parameter usage, and default behavior. No details about output are needed due to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description adds meaning by specifying 'ISO 8601 datetime string to filter apps active since that time', compensating for the schema's lack of parameter description.

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 available Scout APM applications', specifying both the action (list) and resource (applications). It is distinct from sibling tools which are all 'get_*' operations for specific details.

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 explains the optional parameter 'active_since' and its default behavior (thirty-day retention). It provides clear guidance on filtering, though it does not explicitly compare to alternatives or state when not to use the tool.

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