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. 'Manage' does not indicate whether operations are read-only or mutating, what side effects occur, or if permissions are needed. The agent cannot assess safety or impact from the description alone.

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

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

The description is short and front-loaded, but it is under-specified rather than genuinely concise. A single vague phrase does not earn its place because it omits critical operational information that would cost the agent more effort to discover.

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

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

The tool has four parameters, no output schema, and no annotations, so the description must provide substantial context. It fails to mention the two operations, expected return values, or any behavioral constraints, making it inadequate for an agent to invoke the tool confidently without opening the schema.

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

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

Schema description coverage is 100%, with each parameter (cursor, taskId, content, operation) having a descriptive comment and operation having an enum. Since the schema fully documents parameters, the baseline of 3 applies even though the description adds no parameter-level detail.

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

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

The phrase 'Manage comments on tasks' identifies the resource (comments on tasks), which distinguishes it from sibling tools like motion_tasks or motion_projects. However, 'Manage' is a general verb and does not specify the actual operations (list/create) that the schema reveals, so purpose is only partially clear.

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

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

The description offers no guidance on when to choose this tool over alternatives or when to use list versus create. It merely states the resource without any context, exclusions, or conditions, leaving the agent to infer usage from the schema.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals useful conditional behavior (e.g., options[] is mandatory when create uses select/multiSelect, and valueId is used for removals while fieldId is used for additions) but is silent on side effects: delete's destructive nature, whether add/remove operations impact existing tasks and projects, reversibility, or what list returns. The mutating operations are never flagged as writes.

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

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

The purpose is front-loaded and the rest is a dense per-operation parameter matrix with zero fluff; every clause earns its place. The single-paragraph format is less scannable than a structured list would be for a 7-operation dispatcher, but the information density and lack of redundancy make it efficient.

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

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

For a 12-parameter, 7-operation tool with no annotations and no output schema, the description thoroughly covers the required-parameter matrix, which is the primary invocation risk. It leaves meaningful gaps: no indication of return values (especially for list), no warning about the destructive effect of delete or the side effects of add/remove operations, and no error behavior for conflicting inputs.

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

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

Schema description coverage is 100%, so the baseline is 3. The description mostly consolidates constraints already present in the schema (workspaceId/workspaceName alternatives, fieldId vs valueId distinction, options required for select/multiSelect), but it adds value by organizing these constraints into a per-operation quick-reference matrix that reduces the risk of passing the wrong parameter combination.

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

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

The description states a specific resource ('custom fields for tasks and projects') and enumerates seven concrete operations, which clearly distinguishes it from all siblings (none of which concern custom fields). The verb 'Manage' is generic, but the per-operation breakdown with required params makes the purpose concrete and actionable.

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

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

There is no explicit guidance on when to choose this tool over siblings like motion_tasks or motion_projects, so tool-selection usage is only implied by the resource name and operation list. However, the description does give strong intra-tool routing guidance by specifying which params are required for each of the seven operations, effectively telling an agent how to invoke it correctly.

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

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It only restates the operation names and does not mention side effects of create, authentication/permission needs, pagination behavior for list, error cases, or response shapes.

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

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

The description is a single sentence that front-loads the resource and then lists the supported operations. There is no redundant detail or filler, making it appropriately concise and easy to parse.

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

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

This is a multi-operation tool with 7 parameters, operation-dependent requirements, no output schema, and no annotations. The description does not explain which parameters apply to which operation in practice, what a successful create returns, how list results are delivered, or any operational limitations.

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

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

The schema already provides descriptions for all 7 parameters, so the baseline is 3. The description adds no additional parameter-level meaning, but it does not need to because the schema coverage is complete and self-explanatory.

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

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

The description clearly identifies the target resource, 'Motion projects', and enumerates the exact supported operations: create, list, and get. This makes the tool's scope reasonably obvious and distinguishes it from the sibling tools, which target other Motion resources. However, the verb 'Manage' is broad and could imply update/delete operations that are not actually supported.

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

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

The description provides no guidance on when to use this tool versus alternatives, nor when each operation should be selected. An agent is left to infer usage from the operation enum and parameter descriptions in the schema.

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

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

With no annotations provided, the description must carry the behavioral burden, and it does disclose the three operation modes, letting an agent infer read (list) versus mutating (create/delete) behavior. It does not state side effects of delete (e.g., whether the entire recurrence series is removed) or any return/error behavior, leaving a meaningful gap.

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

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

Two sentences, all high-signal: first names the resource, second gives operation-specific required params. No fluff, and the most actionable information is front-loaded.

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

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

For a tool with 15 params, nested frequency objects, and three operations, the description provides the critical operation routing but relies heavily on the schema for optional params and frequency semantics. With no output schema and no annotations, it omits return-value and delete side-effect context, so completeness is adequate but not thorough.

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

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

Input schema coverage is 100%, so the baseline is 3; the description's required-param mapping largely duplicates 'Required for: create/list/delete' already present in the schema properties. It usefully highlights frequency.type as part of create but adds no semantic detail beyond the schema.

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

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

The description identifies the resource (recurring tasks) and enumerates three concrete operations (list/create/delete) in the required-params sentence. It is distinguishable from sibling tools like motion_tasks by the 'recurring' qualifier, though the opening verb 'Manage' is generic.

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

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

The required-params-by-operation breakdown gives clear invocation rules for each operation, which helps an agent choose the operation and fill required fields. It does not, however, explain when recurring tasks should be handled here versus motion_tasks or motion_search, so exclusion/alternative guidance is absent.

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

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

With no annotations, the description carries the full disclosure burden and does so thoroughly: it states all schedules are returned, there is no filtering, the data is limited to recurring working-hour templates, and calendar events/meetings are not exposed. This prevents the agent from misusing the result as free/busy data.

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

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

Three tight sentences front-load the core purpose, then add the no-filtering constraint and the important usage limitation. Every sentence earns its place with no repetition.

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

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

For a simple list-all tool with no required parameters and no output schema, the description is complete: it names the return contents, scope, limitations, and how to get the missing free/busy picture. An agent has enough to invoke it correctly and interpret results.

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

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

The schema already documents the single operation parameter with 100% coverage. The description adds the useful fact that the API supports no filtering, but it does not elaborate on the operation parameter beyond what the enum already conveys.

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

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

The description opens with a specific verb and resource — 'Get all schedules' — and defines the payload as each day's working hours and time zones. It is clearly distinguishable from sibling tools like motion_tasks or motion_statuses because it names schedules as recurring working-hour templates.

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

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

It explicitly notes there are no filtering options and that the result cannot show true free/busy availability, instructing the agent to combine with tasks' scheduledStart/scheduledEnd. This gives clear context for when to use it, though it does not name a sibling tool as the alternative.

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

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

With no annotations, the description carries the burden of behavior disclosure. 'Search' implies read-only and the description names the searched resource types, but it doesn't disclose default scope, operation constraint, result shape, or workspace behavior. It is minimally transparent but not misleading.

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

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

One concise, front-loaded sentence with no filler. It earns its place, though the brevity means some context is handled by the schema rather than the description.

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

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

For a 6-parameter tool with no output schema and no annotations, a single generic sentence is not enough. Missing return-format information, guidance on operation/content, default searchScope, and how to limit by workspace leaves the agent under-informed for correct invocation.

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

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

Schema description coverage is 100%, so the parameters are already documented. The description adds no additional meaning beyond 'query' being central, and there is an internal schema inconsistency: query is described as required but is not in the required array. Baseline 3 is appropriate.

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

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

States a clear action ('Search') and a specific resource set ('Motion tasks and projects'), which distinguishes it from the resource-specific sibling tools like motion_tasks and motion_projects. It doesn't explicitly say it searches across both at once, but the plural scope is reasonably clear.

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

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

No guidance about when to choose this search tool over the dedicated task/project/comment tools, no mention of scoping with workspaceId/workspaceName, and no exclusions. The agent is left to infer usage from the name and schema.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Get' implies a read operation, but the description does not mention response shape, whether results include both task and project statuses, authentication needs, or any limits; it only adds the workspace-scoping information already present in the schema.

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

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

The description is a single, front-loaded sentence with no filler or redundant content. Every word contributes to identifying the tool's purpose and scope.

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

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

For a simple read-only lookup with no required parameters and no output schema, the description is largely sufficient: it states what is returned and for which scope. It does not describe return formatting or the list-only operation, but those are low-risk gaps given the schema's full parameter documentation.

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

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

Schema description coverage is 100%, so the schema already documents operation, workspaceId, and workspaceName. The description adds minimal meaning beyond the schema, naming only the workspace concept; the baseline of 3 is appropriate.

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

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

The description states a specific verb ('Get'), a clear resource ('available task/project statuses'), and a scope ('for a workspace'). This distinguishes it from all listed siblings, which target different resources such as tasks, projects, comments, or custom fields.

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

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

The description implies the tool is used when statuses are needed, but it provides no explicit when-to-use guidance, prerequisites, or comparison with alternative tools. Since no sibling covers statuses, the lack of explicit exclusions is not critical, but the guidance remains only implicit.

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

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

No annotations are provided, so the main description carries the full burden of behavioral disclosure, but it only lists operation names. It does not mention client-side filtering, that list_all_uncompleted spans every workspace, that move is workspace-only, or that delete is destructive. Those details exist in parameter descriptions, but the main description does not provide them.

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

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

The description is a single front-loaded sentence with no filler, enumerating the supported operations efficiently. It could be more informative without becoming bloated, but there is no redundancy or wasted wording.

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

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

For a 21-parameter, eight-operation tool with no annotations and no output schema, this one-line summary is significantly under-specified. Missing high-level context includes operation-specific behavior, return information, and when to use alternative tools; an agent would need to read every parameter description to use it safely.

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

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

The main description adds no parameter-level meaning, but schema description coverage is 100%, so the baseline of 3 applies. All 21 parameters, including operation, status, dueDate, assignee, and autoScheduled, already have detailed explanations in the input schema.

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

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

The description names a concrete resource (Motion tasks) and explicitly lists eight operations, so an agent can recognize this as the task-management tool. It is less crisp than a focused verb-plus-scope phrase because 'Manage' is generic, but the operation list clearly distinguishes it from siblings like motion_comments, motion_search, or motion_recurring_tasks.

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

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

There is no guidance on when to use this tool versus its siblings. The description does not mention alternatives, exclusions, or prerequisites, and it leaves the agent to infer from operation names which request should go here rather than to motion_search, motion_statuses, or motion_recurring_tasks.

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

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

No annotations are provided, so the description carries full responsibility for behavioral disclosure. 'Manage users' misleadingly implies mutating operations, while the schema reveals only read-style operations (list/current). It also does not disclose authentication requirements, side effects, or any limitations.

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

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

The description is compact and front-loads the resource. However, the vague word 'Manage' earns less than a fully tight description like 'List users or get current user information' would, so it is concise but slightly imprecise.

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

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

With no output schema and no annotations, the description leaves important context—operation semantics, filter behavior, and return expectations—unstated. An agent would need to infer most behavior from the input schema alone, making this incomplete for a multi-operation tool.

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

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

Schema description coverage is 100%, so the schema already documents all four parameters. The description adds no extra meaning beyond loosely implying the 'current' operation via 'get current user information', which matches the baseline of 3.

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

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

The description identifies the resource ('users') and one specific operation ('get current user information'), but the leading verb 'Manage' is vague and overstates the scope—the schema only supports 'list' and 'current', not general user management. It does distinguish the tool from sibling tools by resource, but not by operation.

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

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

There is no guidance on when to choose 'list' vs 'current', nor any mention of team/workspace filtering or when this tool should be preferred over alternatives. The only implicit usage signal is that it is user-related, which is not enough for correct operation selection.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It states the operations are list and get, which implies read-only behavior and no destructive side effects, but it provides no additional context about permissions, errors, rate limits, or response behavior.

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

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

The description is a single, front-loaded sentence with no filler. It wastes little space, though 'Manage' is somewhat redundant given the operation list.

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

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

For a simple two-operation tool with a clear schema, the description is adequately complete for selection and invocation. It does not describe return shapes, but no output schema exists and the operations' semantics are straightforward enough to infer.

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

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

The input schema already documents the operation enum and the workspaceId parameter at 100% coverage. The description adds little beyond restating that list and get are supported, so it meets the baseline but does not enhance parameter understanding.

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

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

The description identifies the resource (Motion workspaces) and enumerates the supported operations (list and get), which clearly differentiates it from sibling tools operating on other resources. The word 'Manage' is vague, but the operation list makes the actual scope explicit.

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

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

The description implies this tool is for reading workspace data, but it does not explicitly state when to prefer it over alternatives or mention any exclusions. Since the sibling tools target different resources, the usage context is largely inferable rather than explicitly guided.

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