Server Quality Checklist

Tool Scores

• list_agentsC
  2.9/5.0
  Behavior2/5

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

  The description does not disclose any behavioral traits beyond the action of listing. There are no annotations to indicate read-only or destructive behavior, and the description does not mention authentication, rate limits, or what happens when the roster is empty. The word 'List' implies a read-only operation, but this is implicit rather than explicit.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single sentence that is direct and free of unnecessary words. It covers the primary purpose but is too brief to provide usage context, which slightly reduces its effectiveness compared to a more complete but still concise description.

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

  Completeness3/5

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

  For a simple list tool with one optional parameter and no output schema, the description gives the essential action but omits guidance on alternative tools and the role of the timezone parameter. It is adequate but has clear gaps in contextual framing.

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

  Parameters3/5

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

  The input schema has one optional parameter ('timezone') fully documented in the schema. The description adds no additional meaning about how timezone affects the output, so it relies on the schema's 100% coverage. Baseline of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly specifies the action ('List') and resource ('TaskRouter worker roster') and adds the purpose of capturing each agent's current activity status. However, it does not explicitly differentiate itself from sibling tool 'get_agent_activity', which may offer a related but distinct functionality.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  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 like 'get_agent_activity' or 'search_calls'. The description only states what it does, not the contexts where it is preferred or where other tools should be used.

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

• get_agent_activityA
  3.8/5.0
  Behavior3/5

  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 accurately conveys a read-only retrieval operation and adds a useful detail about explicitly labeled duration sources. However, it does not disclose permissions, data freshness, or any limitations such as pagination or timezone handling beyond the schema. This is adequate but not extra transparent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  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 single clarifying detail. Every word contributes meaning, with no redundancy or unrelated information. This is a model of concise, well-structured documentation.

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

  Completeness4/5

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

  Given the absence of an output schema and annotations, the description provides a solid overview: what data is returned (activity/reservation history, summary statistics), for whom (single worker), and over what period (time window). The schema fully covers parameters, so the description only needs to fill in the outcome, which it does. It omits specifics about the summary statistics' composition, but overall it is sufficiently complete 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.

  Parameters3/5

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

  Schema description coverage is 100%, so each parameter is already fully documented in the schema. The description only references 'time window' and 'single TaskRouter worker', which map directly to existing parameter descriptions without adding new semantic depth. Thus it matches the baseline of 3 for high coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies the verb ('Get'), the specific resource ('activity history and reservation history for a single TaskRouter worker'), and the scope ('over a time window'). This distinguishes it from call-centric sibling tools like search_calls or get_call, which focus on call records rather than worker activity.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The phrase 'for a single TaskRouter worker' implies when this tool is appropriate (per-worker queries) but the description does not explicitly mention alternatives or exclusions. There is no direct comparison to sibling tools or guidance on when not to use this tool, so usage guidance is only implied.

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

• search_callsA
  3.8/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses the return structure (rows plus pagination cursor) and clarifies the meaning of duration fields, explaining that CDR duration and TaskRouter talk time are never conflated. This goes beyond a simple search description and adds valuable behavioral context, though it omits details like authentication or rate limits.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences, front-loaded with the action and scope, and every sentence contributes meaningful detail. It is concise with no filler words, and the structure effectively communicates purpose, return shape, and key nuances.

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

  Completeness4/5

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

  Given the tool has 10 parameters, no output schema, and no annotations, the description does a good job covering the essential usage context: what it filters on, that it returns rows and a pagination cursor, and that duration semantics are explicit. It could have described return fields in more detail, but the provided info is sufficient for an agent to select and invoke the tool reasonably.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the baseline is 3. The description adds a small amount of extra meaning by clarifying duration measurement semantics relevant to min_duration, but the schema already documents each parameter well. The added value is marginal but not absent.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool searches and filters Twilio call records, listing the specific filter dimensions (date range, phone number, direction, etc.). It provides a specific verb and resource, but does not explicitly name sibling tools for differentiation, so it falls just 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.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use the tool (searching and filtering call records) and what it returns (rows plus pagination cursor), but it does not explicitly state when not to use it or mention alternatives like get_call for a single call. This provides some context but no exclusions or alternative references.

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

• get_callA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description must carry the burden of behavioral disclosure. It does disclose that child legs are included and that both CDR duration and TaskRouter talk time are returned with source labels. However, it doesn't mention error handling, required permissions, or that this is a read-only operation, 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences, front-loaded with the core purpose, and includes necessary detail about child legs and duration types. 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.

  Completeness3/5

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

  Given the absence of an output schema and annotations, the description provides useful information about return contents (child legs, two duration types) but does not describe overall response structure, error cases, or other fields like call status or cost. It is sufficient for a basic understanding but not fully comprehensive.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the baseline is 3. The description adds the context of 'single call by SID' and explains what is returned, but it doesn't add extra meaning to the timezone parameter beyond what the schema already says. No significant parameter elaboration.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action ('Get full detail'), resource ('single call'), and selection criteria ('by SID'). It also mentions specific output scope ('including child legs'), which distinguishes it from siblings like search_calls (searching multiple calls) and call_summary (summary view).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage when a specific Call SID is known and full detail is needed, giving clear context. However, it does not explicitly state when not to use this tool vs alternatives like search_calls or call_summary, so it falls short of full exclusion guidance.

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

• get_recordingA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It clearly discloses what is returned (signed URL, expiry, duration, transcript) and what is not (audio bytes). This is significant behavioral context. It doesn't cover errors or permissions, but for a read-only metadata retrieval, this is a reasonable level of disclosure.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences that front-load the primary action and then provide key details. No redundant or filler text. Every word adds value.

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

  Completeness4/5

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

  Given there is no output schema, the description fills that gap by naming the returned fields (signed URL, expiry, duration, transcript) and the explicit exclusion. It is complete for a simple metadata tool, though it doesn't discuss potential error conditions or how timezone affects the response.

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

  Parameters3/5

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

  Schema coverage is 100% and both parameters (call_sid, timezone) have descriptive schema text. The tool description adds context about return values but does not meaningfully enhance the meaning of the parameters beyond what the schema already provides. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Get') and clearly defines the resource ('recording metadata for a call'). It further specifies the exact return contents (signed URL with expiry, duration, transcript) and explicitly excludes audio bytes, making it distinct from sibling tools like get_call or search_calls.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Usage context is implied: it's for a specific call and provides metadata only. The phrase 'Never returns audio bytes' hints at when not to use it, but no explicit alternatives are mentioned (e.g., 'for call details, use get_call'). This is adequate but lacks direct guidance.

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

• call_summaryA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the safety and behavior burden. It discloses a key data integrity guarantee (duration fields carry source labels, CDR and TaskRouter numbers are never mixed) and states return metrics. However, it does not explicitly confirm read-only behavior or potential limitations such as data range sizes, though 'aggregate' and 'returns' strongly imply a non-mutating operation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two succinct sentences with critical information front-loaded: the aggregation verb, dimensions, date range, and return metrics, followed by an important caveat. Every clause adds value with no redundancy.

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

  Completeness4/5

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

  The description covers purpose, acceptable group_by values, date range, high-level return metrics, and a data-source caveat. Given the schema fully documents parameters and no output schema exists, the description provides sufficient high-level context, though it could specify return structure or timezone handling more explicitly.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the description adds limited new parameter information. It does reinforce the meaning of group_by by naming day, agent, or queue, and references date range which maps to start_date/end_date, but the schema already explains these. No additional syntax or format details beyond schema are provided.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies the tool as aggregating call data by day, agent, or queue over a date range, with specific output metrics (counts, talk time, abandonment rate). This verb+resource+scope is distinct from sibling tools like search_calls and get_call, which focus on individual call retrieval.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description conveys a clear use case: when aggregate or summary metrics are needed rather than individual call details. It does not explicitly mention alternatives or exclusions, but the emphasis on aggregation and group-by options implies when this tool is appropriate, making the context clear but not exhaustive.

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