Server Quality Checklist

Tool Scores

• create_groupC
  2.7/5.0
  Behavior2/5

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

  There are no annotations, so the description must carry full behavioral disclosure. It only states that a new group is created, but does not mention idempotency, permissions, response behavior, or error cases. Minimal transparency.

  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 concise sentence with no wasted words. It is appropriately front-loaded, though it could be slightly expanded to include more useful context without becoming verbose.

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

  Completeness1/5

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

  With no annotations, no output schema, and a minimal description, the tool is far from complete. An agent cannot infer expected return values, default behaviors, or edge cases, making the description inadequate for reliable invocation.

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

  Parameters1/5

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

  The schema has 0% description coverage for the 'name' parameter, and the description does not clarify what 'name' means (e.g., format, uniqueness, length). The description adds no value to parameter understanding.

  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 'Create a new worker group' uses a specific verb ('create') and resource ('worker group'), clearly distinguishing it from siblings like create_worker, which creates a worker. It is unambiguous and directly reflects the tool's function.

  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 such as list_groups or delete_group. It does not mention prerequisites, context, or exclusions, leaving the agent without direction on appropriate usage.

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

• update_workerB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavior. It only mentions parameter optionality, but doesn't state side effects, permissions, whether it's a partial update or full replacement, or what the response contains. This is a significant gap for a mutation tool.

  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 a single, clear sentence that is front-loaded with the main action. It avoids unnecessary words and is appropriately sized for the information it conveys.

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

  Completeness1/5

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

  With 13 parameters, no output schema, and no annotations, this description is severely under-specified. It provides no information about return values, side effects, or field-specific semantics, making it inadequate for an agent to confidently invoke the tool.

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

  Parameters2/5

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

  Schema coverage is only 8%, so the description must compensate. It clarifies that all fields are optional except name and task_path, but it doesn't explain any of the other 12 parameters or their purposes. The statement about required fields is helpful but insufficient for an agent to correctly set parameters.

  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 ('Update') and the resource ('existing worker by ID'). It distinguishes itself from sibling tools like create_worker or delete_worker by focusing on modification of existing entities.

  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 'existing worker' implies this tool is for modifying already-created workers, not for creation or deletion. However, it doesn't explicitly mention alternatives or when not to use it, so guidance is only 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.

• create_chainB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral disclosure burden. It adds value by explaining that steps run sequentially by default and that same stage numbers trigger parallel execution, plus the stage integer range. However, it does not disclose side effects, required scheduling behavior, or error handling. It is not misleading but leaves 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 three concise sentences, front-loaded with the core purpose, and adds necessary detail without fluff. Every sentence adds information about behavior or constraints, making it appropriately sized.

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

  Completeness2/5

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

  The tool has 7 parameters, 4 required, including scheduling and notification fields. The description only covers step execution order and stage constraints. It does not explain sched_type, sched_value, notify_on, stop_on_failure, or the requirement of scheduling parameters. No output schema or annotations exist to fill these gaps, leaving the description incomplete for a complex creation 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 only 29% (steps and notify_email have descriptions). The description compensates for the 'steps' parameter by elaborating on stage semantics (sequential vs parallel, range 0-99). However, it adds no explanation for sched_type, sched_value, notify_on, or stop_on_failure, which are undocumented in the schema. It partially adds meaning but does not fully compensate for the low 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 states the function: 'Create a new task chain.' It uses a specific verb+resource and is distinct from sibling tools like delete_chain or run_chain_now. It also adds key behavioral context about step execution order and parallelism, which clarifies what the tool does beyond the name.

  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?

  The description lacks explicit guidance on when to use this tool versus alternatives. It does not mention exclusions or alternatives (e.g., using create_worker for single tasks). The only implicit usage context is that it creates chains, but this is tautological. No prerequisites or conditions are stated.

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

• pause_all_workersA
  3.5/5.0
  Behavior2/5

  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 only states the action ('pause all workers') but fails to mention side effects, reversibility, impact on running tasks, or whether confirmation is needed. This is a significant gap for a bulk mutation 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 a single, front-loaded sentence with no redundant words. It efficiently conveys the core action and scope.

  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 tool has zero parameters and no output schema, the description is minimally viable. However, because this is a bulk operation with potentially disruptive effects, additional context about return values or confirmation behavior would make it more complete.

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

  Parameters4/5

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

  The tool has zero parameters, and the baseline for such cases is 4. The description doesn't need to explain parameter semantics, and there is no schema coverage issue to compensate for.

  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 'Pause' with a clear resource scope 'all workers', instantly distinguishing it from the sibling tool 'pause_worker' which targets individual workers. The phrase 'at once' clarifies the bulk nature of the operation.

  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 'pause_worker'. The description does not mention trade-offs, prerequisites, or scenarios where pausing all workers is appropriate.

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

• run_worker_nowA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description bears the full burden. It only adds 'Logged as MANUAL trigger type,' which gives a minor behavioral detail but fails to disclose potential side effects such as whether the scheduled run will still occur, concurrency handling, permission requirements, or return behavior.

  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 a single sentence with the action verb first, no redundant wording, and no filler. Every word contributes to the core purpose and a single behavioral note.

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

  Completeness2/5

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

  Given there is no output schema and no annotations, the description is too sparse. It doesn't indicate whether the firing is synchronous or asynchronous, what the function returns (e.g., a run ID, status), or error conditions. For a triggering action, this leaves critical operational context missing.

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

  Parameters2/5

  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 not add any meaning beyond the parameter name 'worker_id'—no explanation of how to identify the worker, no source for the ID, no format examples. The sole parameter is obvious from context, but the description doesn't enhance the schema.

  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 ('fire') and a clear resource ('worker') with an explicit scope ('immediately outside its schedule'). It distinguishes itself from sibling tools like pause_worker, delete_worker, and run_chain_now by focusing on immediate manual execution.

  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 phrase 'outside its schedule' clearly indicates the intended use case: triggering a worker manually outside its normal schedule. There is no competing sibling tool for running a worker, so no explicit alternatives are needed, but the context is well implied.

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

• pause_workerA
  3.6/5.0
  Behavior3/5

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

  The description discloses the core toggle behavior (resumes if paused, pauses if running), which is useful. However, it does not mention prerequisites, side effects, error handling, or definitions of 'running' vs 'paused', leaving gaps in behavioral transparency.

  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, direct, and front-loaded with the action. Every sentence adds necessary detail, with no filler or repetition.

  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 toggle action, the description covers the central behavior. However, given the absence of an output schema and annotations, it would benefit from mentioning return values, error scenarios, or state definitions. The simplicity reduces the impact of these omissions.

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

  Parameters2/5

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

  The schema defines worker_id as an integer with no description, and the description only adds 'by ID', which minimally clarifies that it identifies the worker. With 0% schema coverage, this is insufficient to fully understand the parameter's origin or constraints.

  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 ('Toggle pause/resume') and the specific resource ('a worker by ID'). It also explains the toggle semantics, distinguishing it from simple pause/resume and from sibling tools like pause_all_workers.

  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 the tool is used to flip the pause state of a specific worker, but does not explicitly mention alternatives or when to use this versus other worker management tools. Usage guidance is only implied, not explicit.

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

• check_for_updateA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden for behavioral disclosure. 'Check' implies a read-only operation, but there's no mention of network dependency, rate limits, or what the tool does with the result. The description is too sparse to fully inform the agent of 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.

  Conciseness5/5

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

  The description is a single, focused sentence without any wasted words. It is front-loaded and to the point, making it easy to parse and act upon.

  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, parameterless tool, the description covers the core purpose. However, it lacks any mention of the return value or expected output (e.g., a boolean or version number), which could be important for an agent deciding how to act. Given no output schema, this is a notable gap.

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

  Parameters4/5

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

  The tool has zero parameters, so the schema is trivially complete. Per the rubric, a baseline of 4 applies when there are no parameters to describe. The description adds minimal value here but doesn't need to.

  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 tool's function: 'Check GitHub for a newer version of Conductor.' It uses a specific verb ('check') and identifies the resource (GitHub, Conductor version), making it distinct from sibling tools focused on workers, chains, and groups.

  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 purpose inherently implies when to use the tool (to see if an update is available), but no explicit context, exclusions, or alternatives are mentioned. With no similar sibling tools, the lack of explicit guidance is not critical, but it remains minimal.

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

• create_workerA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It discloses important behavioral details like the meaning of timeout_minutes=0 and the expected format for env_vars, which goes beyond the schema. However, it omits other behavioral aspects such as return values, side effects (e.g., whether the worker starts immediately), error handling, or idempotency.

  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 concise (three sentences) and front-loaded with the core purpose. Each sentence adds specific, non-redundant information about schema types and value formats. No filler or repetition, achieving high information density.

  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 tool's complexity (11 parameters, no output schema, no annotations), the description covers only the scheduling and env-var aspects but fails to mention return values, creation behavior, or validation rules. It is adequate for simple use cases but incomplete for predictable invocation in all scenarios.

  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 only 45%, so the description adds value by explaining sched_type formats, timeout_minutes semantics, and env_vars syntax. However, it ignores several parameters (output_dir, new_console, notify_on, etc.) that lack sufficient schema descriptions, leaving gaps in parameter understanding.

  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 ('Register') and resource ('new scheduled worker'), which is specific and distinct from sibling tools like list_workers or update_worker. The additional scheduling format details reinforce the purpose without ambiguity.

  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 implicitly indicates when to use it (creating a new scheduled worker) but does not explicitly contrast with alternatives like update_worker or create_worker_from_template. No exclusions or conditional guidance is provided, so usage context is only implied.

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

• delete_groupA
  3.7/5.0
  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 explicitly discloses a critical side effect: unassigning all members without deleting them. However, it does not mention whether deletion is irreversible or what happens to related groups/chains, leaving a moderate gap.

  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 short sentences, front-loaded with the action, then the key side effect. Every word earns its place; no fluff or repetition.

  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?

  For a simple deletion tool with one parameter, the description covers the core purpose and the most important side effect. It lacks explicit guidance on when to use it, but that is captured under usage guidelines. Overall, it is reasonably complete for its complexity.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description adds no value beyond the schema's 'group_id' name and integer type. The phrase 'by ID' merely restates the parameter name without explaining format, semantics, or how to obtain the ID.

  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 ('Delete a group') and the specific resource ('by ID'), and adds a key distinguishing detail: it unassigns members without deleting them. This separates it from sibling tools like delete_worker or delete_chain.

  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?

  The description does not provide any direct guidance on when to use this tool versus alternatives such as delete_worker or delete_chain. The side effect about members is helpful but does not address usage context or prerequisites.

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

• get_statusA
  3.7/5.0
  Behavior2/5

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

  With no annotations provided, the description must fully disclose behavior. It states that it checks status, implying a read-only operation, but does not describe what 'status' means, what the return format is, whether network calls are made, or any side effects.

  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?

  A single, concise sentence that front-loads the action and resource. No filler or redundant phrasing.

  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?

  The tool is simple (no params, no output schema), but the description could still explain what status information is returned (e.g., running state, database connectivity). As is, it is minimal but adequate for a straightforward health-check tool.

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

  Parameters4/5

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

  The tool has zero parameters, so the baseline is 4. The description correctly adds nothing about parameters, and the empty schema fully covers the parameter space.

  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 'Check' and clearly identifies the resource as 'Conductor's scheduler and database status.' It is distinct from sibling tools like get_logs or list_workers, which deal with different concerns.

  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 usage when one needs to know scheduler or database status, but it provides no explicit guidance on when to choose this tool over alternatives, nor any exclusions or prerequisites.

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

• delete_chainA
  3.8/5.0
  Behavior3/5

  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 that deletion cascades to steps, which is important, but it does not mention permanence, permissions, or error behavior, leaving moderate 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.

  Conciseness5/5

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

  The description is a single sentence, front-loaded with the action, and contains no filler or redundant information.

  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?

  For a one-parameter delete tool, the description covers the core action and cascade scope. It lacks edge-case or permission details but is reasonably complete given the low complexity and lack of output schema.

  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 0%, but the description's 'by ID' clarifies that chain_id is the identifier used for deletion. It does not elaborate on type or format, though chain_id is fairly self-explanatory.

  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 the specific verb 'Delete' and identifies the resource 'chain' plus the cascading scope 'all its steps', clearly distinguishing it from sibling tools like delete_worker and delete_group.

  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 usage for deleting a chain by ID, which is sufficient for a simple delete operation, but it provides no explicit when/when-not guidance or alternatives such as delete_all_workers or run_chain_now.

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

• list_workersA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full burden. It does disclose the output fields and the 'all' scope, but does not mention pagination, ordering, or any operational constraints. This is useful but not comprehensive.

  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 a single, front-loaded sentence that covers the purpose and output fields without waste. Every word earns its place.

  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?

  For a simple 0-parameter list tool with no output schema, the description is complete: it names the resources (workers and chains) and lists all return fields. It could mention pagination or limits, but nothing critical is missing.

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

  Parameters4/5

  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 100% (trivially). Per the rubric, a 0-parameter tool gets a baseline of 4. The description adds no parameter details because none are needed.

  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 tool lists all workers and chains, and enumerates the exact fields returned. This is a specific verb+resource+scope, and the explicit list of output attributes distinguishes it from generic list tools.

  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 given on when to use this tool versus alternatives like list_chains or get_worker_history. Since a sibling list_chains exists, the lack of differentiation is a gap.

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

• run_chain_nowA
  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. It reveals the manual trigger logging and scheduling override, which is useful, but it does not disclose potential side effects, required permissions, or return behavior. More detail would be needed for full transparency.

  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 short sentences, front-loaded, with no extraneous words. Every word adds value: 'immediately', 'outside its schedule', and 'logged as MANUAL trigger' are all meaningful.

  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 one-parameter trigger, the description covers the core behavior, but given the absence of annotations and output schema, it omits return values, error conditions, and any preconditions. It is minimally viable but not fully complete.

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

  Parameters2/5

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

  The schema has one required parameter (chain_id) and 0% description coverage. The description does not explain the parameter's purpose or format; it only references 'a chain'. While the parameter name is fairly self-explanatory, the low coverage demands compensation that is absent.

  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 ('Fire a chain'), the resource ('chain'), and the specific context ('outside its schedule'), effectively distinguishing it from sibling tools like run_worker_now. The verb 'fire' is specific enough in this context.

  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 provides clear context for when to use the tool: immediate execution outside the normal schedule, and mentions it is logged as MANUAL. However, it does not explicitly state alternatives or exclusions, 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.

• delete_workerA
  4/5.0
  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 of disclosure. It discloses the key behavioral trait that deletion is permanent and affects both scheduler and database, which goes beyond a simple 'delete' statement. However, it doesn't mention reversibility, required permissions, or side effects on associated history.

  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 extremely concise—two sentences, front-loaded with the action and resource, followed by a clarifying effect. Every word earns its place, with no filler.

  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?

  For a simple delete operation with a single parameter and no output schema, the description provides enough context: what it does, the scope (worker), and the effect (scheduler + database). It could mention return values or cascading effects, but these are not essential for this simple 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?

  The schema has one parameter (worker_id) and description coverage is 0%. The description adds minimal value by saying 'by ID,' which clarifies the parameter's role as an identifier, but it doesn't explain the type or where to obtain the ID beyond what the schema already provides.

  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 (delete) and the resource (worker by ID), and specifies the scope by noting it 'Removes from scheduler and database.' This distinguishes it from sibling tools like pause_worker or delete_all_workers.

  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 use for deleting a single worker by ID, but it doesn't explicitly mention when not to use it or provide alternatives (e.g., pause_worker for temporary suspension). The context is clear but lacks explicit exclusions or comparison with siblings.

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

• get_logsA
  4/5.0
  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 a key behavioral trait: the 500-entry ring buffer with oldest entries dropping off. It also lists log levels, which helps the agent know what types of entries may appear. However, it does not mention whether the buffer is persistent in memory, whether any side effects occur on read, or authentication requirements—minor gaps given the simplicity.

  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?

  Three concise sentences, each conveying necessary information: purpose, offset usage, and buffer/log-level details. There is no fluff or repetition, and the most important information is front-loaded.

  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?

  For a simple parameterless (or single optional parameter) log retrieval tool, the description is quite complete. It explains the parameter semantics, the log levels, and the buffer limit. With no output schema, it could have described the structure of returned entries, but the context is sufficient for an agent to understand what this tool does and how to call it.

  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 already provides a clear description for the 'since' parameter ('Return entries after this offset index') with a default of 0, so schema coverage is 100%. The description adds only a minor clarification ('use 0 for all'), which is redundant given the schema's default. It does not add significant meaning beyond the schema.

  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 states a specific action ('Get debug log entries') and a clear resource (logs). It is immediately distinguishable from all sibling tools, which focus on workers, chains, groups, and settings. The additional details about offset and log levels reinforce the purpose.

  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 usage for retrieving debug logs and explains the offset behavior, but it does not explicitly state when to use this tool versus alternatives or mention any exclusions. It is clear enough from context, but no explicit guidance is provided.

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

• save_email_settingsA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description bears the full burden of behavioral disclosure. It usefully explains the credential type (App Password, not regular) and the 2-Step Verification prerequisite. However, it does not mention potential side effects such as overwriting existing settings, which would be expected for a save/mutation tool.

  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 concise sentences with the purpose front-loaded. The second sentence adds essential prerequisite and setup information, including a direct link, without any redundant or wasted wording.

  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?

  For a simple two-parameter settings tool, the description covers the operation and prerequisites well. It lacks explicit mention of whether saving overwrites existing credentials, but this is a minor omission given the tool's seemingly straightforward save behavior.

  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 already provides descriptions for both parameters (email and password) with 100% coverage. The description adds context about the App Password generation link and the 2-Step Verification requirement, but this supplemental information does not significantly change how to use the parameters.

  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 action ('Save') and the resource ('Gmail credentials for email notifications and templates'), which is specific and distinguishes it from the sibling tool get_email_settings. It conveys exactly what the tool does without ambiguity.

  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 provides clear context for when to use the tool: when saving Gmail credentials for notifications/templates, and it explains the necessary prerequisites (2-Step Verification, App Password). It does not explicitly contrast with alternatives or state when not to use it, but the context is sufficient.

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

• create_worker_from_templateA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description adds 'Generated scripts use stdlib only' and lists config fields, but does not disclose default worker state, email side effects, or permissions. It provides some behavioral context but not full transparency.

  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, concisely listing template types and configs without extraneous information. It is front-loaded with the purpose and efficiently organized.

  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?

  For a tool with 6 template types and nested config, the description provides enough context to construct a valid invocation. It omits return value and post-creation behavior, but the critical template-config mapping is covered.

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

  Parameters4/5

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

  The description maps each template_type to its required config fields (e.g., folder_backup: source, dest, keep, summary_email), which is essential since the schema only provides a vague 'Template-specific config fields' description for config.

  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 'Create a worker using a built-in template' and enumerates specific template types, making the tool's purpose explicit and distinguishing it from the generic create_worker sibling.

  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 for template-based workers by listing available template types, but does not explicitly contrast with create_worker or state when not to use it. Clear context is present without explicit exclusions.

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

• delete_all_workersA
  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 full burden. It discloses the critical behavioral trait of irreversibility ('Irreversible') and the broad scope ('ALL workers and chains'). It does not mention auth requirements or post-deletion effects, but the most important destructive aspects are covered.

  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 extremely concise: 'Delete ALL workers and chains. Irreversible. Use with caution.' Every sentence provides essential information: what it does, its irreversibility, and a warning. No words are wasted.

  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's simplicity (no parameters, no output schema) and the destructive nature, the description covers the key points: scope and irreversibility. It could mention prerequisites or what exactly happens to related data, but for a zero-parameter tool, it is adequately complete.

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

  Parameters4/5

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

  The tool has zero parameters, and the schema is empty. Per the rubric, the baseline for 0 params is 4. The description adds no parameter-specific information, but none is needed since there are no arguments to clarify.

  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 tool's function: 'Delete ALL workers and chains.' This is a specific verb+resource+scope, and it distinguishes itself from sibling tools like delete_worker and delete_chain by explicitly covering all workers and chains.

  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 provides a caution ('Use with caution') but lacks explicit guidance on when to use this tool versus alternatives like delete_worker or delete_chain. The intended use (bulk deletion of everything) is implied rather than stated, and no exclusions or alternative recommendations are provided.

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

• export_allA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It states what is exported and the output format (JSON snapshot), which implies a read-only operation. However, it does not mention potential side effects, size limitations, or whether sensitive data (e.g., credentials) is included. This is adequate but not rich.

  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: the first states the action and scope, the second states the use cases. It is front-loaded and every sentence provides value. No filler or 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?

  For a simple tool with no parameters, no annotations, and no output schema, the description is mostly complete. It identifies the resources exported and the output format, and gives common use cases. It could briefly mention the result or any limitations, but the information is sufficient for an agent to select and invoke the tool correctly.

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

  Parameters4/5

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

  The tool has zero parameters, so the schema coverage is trivially 100%. The description adds no parameter specifics because none exist, which is appropriate. The baseline for 0 params is 4, and the description does not need to compensate.

  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 verb 'Export' and the specific resources (workers, chains, chain steps, groups) with an explicit output format (JSON snapshot). This distinguishes it from sibling tools like list_workers or delete_all_workers by describing a distinct bulk export action.

  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 explicitly identifies use cases: 'Use for backup or migration.' This gives clear context for when this tool is appropriate. It doesn't explicitly exclude alternatives, but the export-all nature is distinct enough from list/delete operations to make misuse unlikely.

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

• list_groupsA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It correctly implies a read-only listing operation and adds conceptual context ('collapsible collections of workers and chains'), but it doesn't elaborate on return format, pagination, or any edge cases. For a simple list, this is adequate but not rich.

  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 crisp sentences: the first states the action, the second clarifies the domain concept. No filler, front-loaded, and every word earns its place.

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

  Completeness5/5

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

  Given the tool is a zero-parameter read-only list and there is no output schema, the description fully covers what the agent needs to know: what it does and what a 'group' is. 'List all' clearly implies the return value. Nothing significant is missing.

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

  Parameters4/5

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

  There are zero parameters and the schema is empty, so the description has no parameter burden. The baseline for 0 params is 4, and the description doesn't need to compensate for any missing schema information.

  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 'List all worker groups' with a specific verb and resource. It distinguishes from sibling tools like list_workers and list_chains by clarifying what a group is. This is a textbook example of clear purpose.

  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 context for when to use this tool is clear: to retrieve all worker groups. It doesn't explicitly mention alternatives or exclusions, but the sibling tool names provide natural differentiation (e.g., list_workers for workers, create_group/delete_group for management). No ambiguity for a zero-parameter read-only operation.

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

• get_chain_historyA
  4.4/5.0
  Behavior4/5

  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 discloses the read-only nature via 'Get' and the behavior of returning exactly the last 10 entries, which is useful. However, it does not mention ordering, return format, or error conditions.

  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 a single, front-loaded sentence that conveys all essential information without any unnecessary words or repetition.

  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?

  For a simple read tool with one required parameter and no output schema, the description covers the core aspects: what is retrieved and the limit of 10. It lacks explicit return structure details, but the low complexity and the phrase 'run history entries' provide adequate guidance.

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

  Parameters4/5

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

  Although schema description coverage is 0%, the sole parameter chain_id is self-explanatory from the tool name and the mention of 'a chain' in the description. The description adds minimal but sufficient context for a single, obvious parameter.

  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', the resource 'run history entries', and the scope 'for a chain'. It effectively distinguishes from sibling tools like get_worker_history by specifying the chain context.

  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 the use case: retrieving recent run history for a specific chain. It does not explicitly contrast with alternatives like get_worker_history, but the purpose is clear enough that an agent would know when to invoke it.

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

• get_email_settingsA
  4.5/5.0
  Behavior4/5

  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 return values (has_credentials, sender email) and provides an actionable instruction if not configured. This gives the agent a clear understanding of the tool's behavior and expected follow-up, even without explicitly stating it is read-only, which the verb 'check' implies.

  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 three sentences, front-loaded with the core purpose. Every sentence earns its place: purpose, return values, and usage guidance. There is no fluff or repetition, making it highly concise and well-structured.

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

  Completeness5/5

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

  For a simple tool with no parameters and no output schema, the description is complete. It explains what the tool returns, when to use it, and what to do based on the result. This is sufficient for an agent to select and invoke the tool correctly in context.

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

  Parameters4/5

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

  The tool has zero parameters, and the schema description coverage is 100% (empty schema). The baseline for 0 params is 4, and the description correctly focuses on the output rather than parameters, which adds appropriate value without redundancy.

  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 tool's function with a specific verb and resource: 'Check if email credentials are configured.' It distinguishes itself from sibling tools like save_email_settings, which is the setter companion, and from unrelated tools like get_status. The purpose is unambiguous.

  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 explicitly states when to use it: 'Use this before any email-related operation to verify setup.' This is clear context, but it does not mention explicit alternatives or when not to use the tool, as the 'when-not' is inferred by its role. Still, the usage direction is strong.

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

• get_worker_historyA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden. It discloses the result limit (last 10) and the exact fields returned, which is valuable for a read operation. It doesn't mention error behavior or prerequisites, but for a simple get tool this 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.

  Conciseness5/5

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

  The description is two short sentences with no filler. It front-loads the action and object, making it immediately understandable.

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

  Completeness5/5

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

  Despite the lack of an output schema, the description covers the essential return fields and the limit, making it complete for this simple tool. No other context is needed.

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

  Parameters4/5

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

  The only parameter, worker_id, is a simple integer and its meaning is self-evident. The description's phrase 'for a worker' reinforces the parameter's purpose. No additional description is needed for this trivial parameter.

  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') and the resource ('last 10 run history entries for a worker'). It distinguishes this tool from siblings like get_chain_history by explicitly targeting worker history.

  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 context is clear: this tool is for retrieving a worker's run history. It does not explicitly mention when not to use it or name alternatives, but the sibling tools list makes its scope obvious. The 'last 10' limitation further clarifies usage.

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

• list_chainsA
  4.5/5.0
  Behavior4/5

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

  Although no annotations are provided, the description signals a read-only operation via 'List' and enumerates the return fields, giving a transparent view of expected output without hidden side effects.

  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?

  Single sentence, front-loaded with the action, then a compact enumeration of output fields. Zero wasted words.

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

  Completeness5/5

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

  The description fully covers the tool's purpose and return value structure in the absence of an output schema. It explains what the user will receive, making it complete for a parameterless list operation.

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

  Parameters4/5

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

  The tool has zero parameters; the schema is empty with 100% coverage. The description need not add parameter details, so the baseline score of 4 applies.

  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?

  Clearly states 'List all task chains' – a specific verb+resource scope. Distinct from sibling list_workers and list_groups, and from chain mutation tools like create_chain or run_chain_now.

  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 clearly implies the use case: to retrieve all task chains. It does not explicitly mention alternatives, but the context is unambiguous for a listing operation.

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