FavCRM

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

The description adds behavioral context beyond annotations: it sends a 6-digit code to the email and is non-idempotent. This aligns with the readOnlyHint=false and idempotentHint=false annotations without contradiction.

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 concise sentences: first covers the action and outcome, second provides the next step. No wasted words, front-loaded with key information.

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

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

Given the output schema exists, the description doesn't need to detail returns. It adequately sets up the two-step workflow and provides necessary context. Could mention error cases but overall complete.

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

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

The description explains the token's origin (from create_team_member_invite or invite link), adding value beyond the schema's description. Since schema coverage is 100%, the description enhances 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 clearly states the tool's purpose: validates an invite token and sends a verification code, identifying it as step 1 of a two-step process. It distinguishes from the sibling tool by naming the next step.

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 tells the agent to use this as the first step after obtaining an invite token and then call accept_team_invite_verify. It provides clear workflow context but does not explicitly list when not to use it.

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

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

Annotations provide no guidance (all false), so the description carries full burden. It discloses the core actions (verify, join, return key) but lacks details on side effects, error handling, or idempotency. This is adequate 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.

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

The description is two sentences, front-loaded with 'Step 2', and contains no extraneous information. Every word serves a purpose, making it highly concise.

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

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

Given the complexity (2-step process, 3 parameters, output schema), the description covers the overall purpose and outcome. However, it omits prerequisites (e.g., having a valid invite token from step 1) and error cases. It is mostly complete but has gaps.

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 description adds little beyond the schema. It mentions 'emailed code' and 'invite token' but doesn't enhance understanding of parameter semantics beyond what the schema already provides.

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

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

The description clearly states 'Step 2 of agentic team invite acceptance' and details the actions: verifies code, joins user, returns API key. It distinguishes from the sibling tool accept_team_invite_request by positioning itself as the second step.

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

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

The description explicitly labels itself as 'Step 2', indicating it follows accept_team_invite_request. While it doesn't list contraindications or alternative scenarios, the step ordering provides clear usage context.

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

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

Annotations indicate this is a write operation (readOnlyHint=false) and not destructive. The description adds that the document is stored as a single piece and that embedding/retrieval happens elsewhere, providing useful behavioral context beyond annotations.

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 two sentences, each adding value. The first states the primary action, the second provides usage examples and storage details. No fluff or 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 creation tool with 2 parameters and no enums, the description covers purpose, usage, and behavioral details. The presence of an output schema means return values need not be described. All necessary context is present.

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 covers both parameters (name, content) with descriptions. The description does not add significant semantics beyond stating the document is 'free-form text.' With 100% schema coverage, the baseline is 3, and the description does not elevate it.

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

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

The description clearly states the action ('Add') and the resource ('free-form text document to the knowledge base'). It distinguishes from sibling tools like scrape_knowledge_url and list_knowledge_documents by specifying the type of content (policies, FAQs, notes).

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

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

The description provides clear examples of when to use the tool ('pasted policies, FAQs, internal notes, brand voice references'). It does not explicitly mention when not to use or alternatives, but the context is sufficient for correct 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?

Annotations are present but neutral (readOnlyHint=false, destructiveHint=false). The description lacks additional behavioral details such as side effects, error handling, or return value structure. It only restates input requirements from 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?

Extremely concise with two sentences. The first sentence states the core action, and the second provides essential details about block format and types. No wasted words.

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

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

For a complex tool with many block types, the description is too sparse. It omits output description, error conditions, and prerequisites. The output schema exists but is not referenced.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds a summary of the block structure and lists block types, offering some consolidation beyond the schema, but does not significantly deepen 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 clearly states the action ('Append one or more blocks to the end of a post') with a specific verb and resource. It distinguishes this tool from siblings like remove_post_block or reorder_post_blocks, though it does not explicitly contrast them.

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 on when to use this tool vs alternatives. The description does not mention prerequisites, when-not-to-use, or provide examples. Agents must infer from the name and sibling context.

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

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

Adds context beyond annotations: explains effect on survey lists (removing from active lists). Annotations give destructive and idempotent hints; description aligns and provides additional behavioral detail.

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?

Single concise sentence with no wasted words. Front-loaded with verb and resource.

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?

Tool is simple (1 param, output schema exists, annotations present). Description sufficiently covers purpose and effect; no gaps.

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?

Only parameter surveyId is described in schema with same wording. No extra semantic beyond schema, but schema coverage is 100%, so baseline 3 applies.

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?

Description clearly states the action ('Archive') and resource ('survey') with specific outcome ('remove from active survey lists'). Distinguishes from sibling survey tools like create, update, delete, list.

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?

Implied usage via name and description, but no explicit guidance on when to use versus alternatives like delete_survey or toggle active status.

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?

Annotations declare readOnlyHint=false, indicating mutation, which is consistent with 'Assign'. However, the description does not disclose additional behavioral traits such as whether the operation is idempotent, what happens if the user is already assigned (e.g., error or replacement), or any side effects. With annotations carrying the burden, the description adds minimal behavioral context.

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

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

The description consists of two concise, front-loaded sentences with no extraneous information. Each sentence serves a clear purpose: stating the action and providing a parameter hint.

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 tool with two parameters and an output schema present, the description adequately covers the core functionality and a critical parameter hint. It could optionally mention whether the assignment replaces existing ones, but overall it is sufficient for an agent to invoke the tool correctly.

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 covers both parameters with descriptions, achieving 100% coverage. The description adds value by specifying the source for 'userId' ('users.id from list_staff.userId'), which provides practical context beyond the schema's generic description.

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

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

The description clearly states the action ('Assign a staff member to a booking service') and the resource involved, making the tool's purpose unmistakable. It also distinguishes from siblings like 'link_resource_to_service' by specifying 'staff member' and 'booking service'.

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 a hint on where to get the userId ('from list_staff.userId'), implying a prerequisite step. However, it lacks explicit guidance on when to use this tool versus alternatives, such as when a service already has staff assigned or how to handle existing assignments.

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?

Annotations provide readOnlyHint=false (write operation) but no other behavioral hints. The description adds value by disclosing credit behavior (no extra charge) and verification (job ownership and success). However, it omits the polling behavior (pollIfRunning/pollTimeoutMs) which is critical for understanding execution flow. With existing annotations, the description adds moderate context but leaves a significant 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?

The description is three sentences, each serving a distinct purpose: action statement, usage scenario, and behavioral note. It is front-loaded with the primary action. No extraneous information, 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.

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

Given the tool's complexity (5 parameters, output schema, annotations), the description covers purpose, usage scenarios, verification, and credit policy. However, it fails to mention the polling mechanism, which is a key part of the tool's behavior. This omission reduces completeness slightly, but overall the description is adequate for agent decision-making.

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

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

Schema coverage is 100% for all 5 parameters, so the baseline is 3. The description does not add substantial meaning beyond the schema; it only indirectly references polling ('job kept running') but does not explain the polling parameters. Thus, it meets the baseline without exceeding it.

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

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

The description clearly states the action ('attach'), the target resource ('post's featuredImage'), and the source ('ai-media job's output'). It distinguishes from siblings like 'generate_post_cover' by specifying use cases (timeout or reuse). This is a specific verb+resource pair with explicit differentiation.

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

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

The description explicitly states when to use: 'Use when generate_post_cover timed out... or when reusing the same generation across multiple posts.' It also notes verifications and credit policy. However, it does not explicitly mention when not to use or alternative tools like 'upload_post_cover_from_url'.

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?

Annotations already indicate readOnlyHint=false and destructiveHint=false. Description adds no new behavioral traits such as idempotency, side effects, or permission requirements. It misses an opportunity to clarify whether attaching tags multiple times adds or replaces tags.

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, no wasted words. First sentence states action, second provides usage context. Concise and well-structured.

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

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

Given the tool's simplicity and presence of an output schema, the description covers purpose and context adequately. Could be improved by mentioning idempotency or behavior on multiple calls, but overall sufficient.

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

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

Schema coverage is 100%, so parameters are already described. The description adds context ('segmented members') which relates to accountIds, but does not add new parameter-specific details. Baseline score 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?

Description uses specific verb 'attach' and identifies resource 'tags to a member/account'. It clearly states the action and includes a use case ('segmenting members after filtering'), which distinguishes it from sibling tools like list_tags.

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?

Description hints at when to use ('after filtering'), but does not explicitly mention when not to use or provide alternative tool names. The context is helpful but not exhaustive.

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?

Annotations already set destructiveHint: true, so the destructive nature is clear. Description adds that a reason can be provided, but does not disclose further behavioral traits like permissions, reversibility, or 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.

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

Two short sentences, no wasted words. Efficient but could be improved with structured bullet points or additional context.

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

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

With an output schema present, return values are documented elsewhere. However, for a destructive operation, more context about consequences (e.g., booking status changes, refunds) would be beneficial.

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

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

Input schema has 100% coverage of parameters with descriptions. Description only notes 'Optionally provide a reason', which repeats the schema's optionality and adds no new meaning.

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?

Description clearly states 'Cancel a booking' with a specific verb and resource. Among sibling tools, there is no other 'cancel' tool except cancel_subscription, so it is distinct.

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?

Description provides no guidance on when to use this tool vs alternatives (e.g., complete_booking, confirm_booking), no prerequisites or status conditions, and no exclusions.

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?

Annotations already mark destructiveHint true; description adds details about turning off auto-renew and preventing further billing cycles, adding value beyond the hint.

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, front-loaded with purpose, no wasted words. Efficient and informative.

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

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

Given the simple tool (1 param, output schema exists), description covers purpose, behavior, and effect completely.

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

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

Schema coverage is 100% and the only parameter 'subscriptionId' is described in schema. Description adds no extra semantics beyond the schema.

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

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

The description clearly states 'Cancel a subscription' with a specific verb and resource, and distinguishes from siblings like 'pause_subscription' by noting it is destructive and stops auto-renew.

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

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

The description provides clear context on when to use (to stop future billing) and effects (existing period stays valid), but does not explicitly mention alternatives like 'pause_subscription'.

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?

Annotations already declare the tool as read-only and idempotent. The description adds detailed behavioral context about what it checks (token scopes, modules, subscription state, quota) and notes that quota checks are single-resource preflights, fully disclosing behavior beyond annotations.

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, well-structured sentence that front-loads the purpose and efficiently conveys all necessary information without redundancy or waste.

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

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

Given the tool's moderate complexity, the presence of an output schema, and the description covering what is checked and how to specify the operation, it provides complete context for an agent to correctly select and invoke the tool.

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

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

Schema coverage is 100% with good parameter descriptions. The description adds value by summarizing the high-level usage pattern (provide one of toolName, quotaCode, or moduleCode) and clarifying that delta is for planned usage increment, which enhances understanding beyond the schema alone.

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

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

The description clearly states the tool's purpose as a preflight check for whether an operation is allowed based on token scopes, enabled modules, subscription state, and quota. It specifies the parameters (toolName, quotaCode, moduleCode) and distinguishes itself from sibling tools by focusing on authorization checks rather than status retrieval or listing.

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

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

The description implies usage before performing an operation to verify permissions, and instructs to provide one of the three identifier types. While it does not explicitly exclude alternatives, the context is clear and appropriate given the lack of directly competing sibling tools.

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

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

Annotations declare non-destructive (destructiveHint=false) and non-idempotent. The description adds that the copy is created in DRAFT status and name gets '(Copy)' appended, providing useful behavioral context beyond annotations.

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, zero waste. Front-loaded with key action and entity types. Efficient and clear.

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

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

Given the existence of an output schema, the description adequately covers cloning behavior, draft status, and naming. It doesn't detail handling of related data, but for a clone tool this is sufficient.

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

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

Schema coverage is 100%. The description adds that 'name' can override the default naming, but otherwise the schema already describes parameters adequately. 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?

The description clearly states the tool duplicates existing records and creates a copy in DRAFT status with '(Copy)' appended. It distinguishes from create_* siblings by specifying it creates a copy, not a new blank record.

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

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

The description implies usage for cloning when you need a copy of an existing record, but no explicit guidance on when not to use it or prerequisites. Not as strong as explicit alternatives.

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?

Annotations provide no safety hints (readOnlyHint, destructiveHint false). The description discloses the mutating behavior (creates/updates, applies values) but does not discuss error handling, rollback, or idempotency implications. More detail on failure scenarios would improve transparency.

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

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

Two sentences with no redundancy. The first sentence specifies the prerequisite and input identity, the second explains the effect. Every word contributes.

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

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

Given the presence of an output schema and a relatively straightforward commit action, the description effectively communicates the tool's purpose and input requirements. It links to the preview tool and mentions the key effects. Could mention the row limit or validation constraints, but these are in 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 coverage is 50%, with many fields already described in the schema. The description adds value by highlighting that points, stamps, and credit deltas are applied, which is not evident from the schema alone. However, it does not compensate fully for undocumented fields.

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

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

The description clearly states the tool commits a previewed customer import, specifying the exact inputs (same rows and sessionId from preview_customer_import) and the effects (creates/updates accounts, applies points/stamps/credit). This distinguishes it from sibling tools like preview_customer_import.

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

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

The description explicitly tells when to use: after preview and with matching rows and sessionId. It does not explicitly mention when not to use or alternative tools, but the usage context is clear for a commit operation tied to a specific preview step.

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?

Annotations already note it's non-readOnly (data mutation) and non-destructive. The description adds value by disclosing the commission calculation side effect, which is important for agent decision-making.

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

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

Two efficient sentences with no fluff. The description is front-loaded with the primary action and the side effect. Every sentence earns its place.

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

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

The tool has an output schema (context signals indicate true), so description is not burdened to explain returns. The core action and side effect are covered, but missing potential error conditions or prerequisites (e.g., booking must exist). Adequate for a simple tool.

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

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

Schema coverage is 100% with a clear description for the only parameter (bookingId). The description does not add any further semantic meaning beyond what the schema already provides.

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

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

The description clearly states the action: 'Mark a booking as completed' and adds a specific side effect ('Triggers commission calculation if configured'). This distinguishes it from sibling tools like cancel_booking, confirm_booking, or create_booking.

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 on when to use this tool versus alternatives. No prerequisites, no exclusions, and no mention of conditions like booking status requirements. The description is silent on usage context.

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

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

Annotations indicate non-read-only and non-destructive, but the description adds no behavioral insight beyond the verb 'confirm'. Missing details like state changes or 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.

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

Extremely concise: a single, clear sentence with no unnecessary words. Front-loaded with the key action and resource.

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

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

Given the single parameter and existence of an output schema, the description is nearly sufficient. However, it could briefly state the effect on booking status to be fully self-contained.

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

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

Schema coverage is 100%, so the schema already documents the parameter. The description adds no additional meaning beyond the schema's parameter description.

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

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

The description clearly states the action ('confirm') and the resource ('a pending booking'), which directly distinguishes it from siblings like cancel_booking and complete_booking.

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 on when to use this tool versus alternatives like cancel_booking or complete_booking. The description provides no context for proper usage.

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?

Annotations provide no safety hints. Description adds that it creates an account and optionally enrolls membership, but does not disclose side effects like duplicate handling, required permissions, or if a welcome email is sent. Behavior is partially transparent.

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 front-load the main action and include a key usage tip. No unnecessary words; every sentence earns its place.

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

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

Given the tool's complexity (13 parameters, nested objects), the description is brief. It covers the main action and optional enrollment but omits context like company scope, prerequisites, or what 'primary contact' entails. Could be more complete but is acceptable with the output schema assumed to handle return values.

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

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

Schema coverage is 100%, so parameters are already documented. Description adds context like 'with a primary contact' and 'optionally enroll' which relate to some parameters but does not significantly enhance individual parameter meaning beyond schema descriptions.

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

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

Description clearly states 'Create a CRM account/customer with a primary contact', using a specific verb and resource. It distinguishes itself from the sibling tool 'enrol_membership' by explicitly recommending its use for existing accounts.

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?

Explicitly tells when to use this tool (to create an account and optionally enroll) and when to use the alternative 'enrol_membership' (for existing accounts). This provides clear guidance on tool 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?

Annotations already declare readOnlyHint=false and destructiveHint=false, indicating mutation without destruction. The description adds no further behavioral context (e.g., conflicts, notifications). It is adequate but not enhanced beyond annotations.

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, front-loaded with action and prerequisite, no unnecessary words. Highly efficient and structured functionally.

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

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

While the description mentions a prerequisite and key parameters, it lacks details on error handling, conflict resolution, or output. Given the existence of an output schema (not shown) and high schema coverage, the description is minimally complete but could be improved.

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

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

Schema coverage is 100% with descriptions for all parameters. The description lists key parameters (service, member, date, time) but adds no extra meaning beyond what the schema provides. Baseline score 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 clearly states the action 'Create a new booking for a member' and distinguishes it from sibling tools like cancel_booking, complete_booking, etc. It uses specific verb-resource pairing and provides prerequisite context.

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

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

The description explicitly advises using get_available_slots first, then creating the booking with key parameters. It provides a clear workflow hint, though it doesn't specify when not to use this tool or alternatives.

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

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

The description adds behavioral context beyond annotations: it reveals the draft-only nature and the admin review requirement. No contradictions with annotations (readOnlyHint=false, etc.). It could mention more about state or default channel, but the given info is helpful.

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, front-loading the key purpose and critical behavior. No redundancy, every sentence earns its place.

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

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

Given the existence of an output schema and good annotations, the description is sufficiently complete. It covers the essential draft behavior and sending flow. It could mention the required name parameter, but schema already handles that.

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

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

Schema coverage is 100% with descriptions. The description adds context about the draft status, which is not in the schema, providing meaning beyond parameter names. This justifies a score above 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 clearly states the specific action ('create a DRAFT... broadcast campaign'), the two channels (WhatsApp, SMS), and explicitly differentiates from sending by noting that it is not sent but requires admin review.

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

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

The description provides clear context on when to use this tool (to create a draft broadcast) and informs that the broadcast must be sent from another page, implying that this tool is not for sending. However, it does not explicitly list alternatives or conditions when not to use.

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?

Adds useful behavioral details beyond annotations: default status is DRAFT, recipientSource='list' is an alias, and channelConfig recommendations for email. Annotations already indicate readOnlyHint=false (write) and destructiveHint=false, but the description enriches the understanding of the tool's 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?

Extremely concise: two sentences that convey purpose, default state, key parameter usage, and an alias. No superfluous information, front-loaded with the core action.

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?

Covers most relevant aspects: channels, default status, channelConfig hints, alias. Could mention that status can also be SCHEDULED (per schema) and give more context on segmentation, but the output schema and high schema coverage compensate. Overall well-rounded for a creation tool.

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

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

Schema coverage is 100%, so parameters are already described. The description adds value by clarifying email channelConfig composition and the alias behavior for recipientSource. This extra context is helpful but not extensive, earning a baseline-adjusted score 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?

Clearly states action ('Create') and resource ('marketing campaign') with supported channels (email, SMS, WhatsApp). However, does not explicitly differentiate from sibling tools like update_campaign or delete_campaign, though the creation context is implied by 'in DRAFT'.

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

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

Provides specific guidance on channelConfig fields and recipientSource alias, but lacks explicit when-to-use or when-not-to-use advice relative to other campaign tools. The context is implied but not clearly stated.

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

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

Annotations already indicate readOnlyHint=false. Description adds no further behavioral context beyond the basic create action.

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 concise sentences, front-loaded with the main action, no wasted words.

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

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

For a simple create tool with output schema and annotations, the description adequately covers purpose and a key naming guideline, though it could mention constraints like character limits.

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 covers all 4 parameters with descriptions. Description adds only a naming convention hint for the 'name' parameter, not enough to exceed baseline.

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

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

The description clearly states 'Create a CMS post category' with examples, distinguishing it from sibling tools like update_category and delete_category.

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

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

Provides guidance on using namespaced names for sub-categories, but does not explicitly state when to use this tool vs. alternatives or mention prerequisites.

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?

Annotations indicate the tool is not read-only and not destructive, which is consistent with creating a contact. The description adds no further behavioral details beyond the basic operation, making it 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.

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

The description is a single concise sentence with no unnecessary words. It is front-loaded with the essential action and resource, though it could include more detail without becoming verbose.

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

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

Given the 6 parameters and existence of an output schema, the description covers the basic purpose but lacks details on prerequisites, error conditions, or typical use cases. It is minimally complete for a simple create operation.

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

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

The input schema has 100% description coverage, so each parameter is already documented. The tool description does not add any additional meaning or clarify relationships between parameters, meeting the baseline for coverage.

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

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

The description uses a specific verb 'Create' and clearly identifies the resource as a contact on an existing CRM account. This distinguishes it from other create tools like create_account or create_booking, and from sibling tools such as update_contact and list_contacts.

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

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

The description does not provide guidance on when to use this tool versus alternatives like update_contact. It implies that an existing account is required but does not explicitly state prerequisites or scenarios where this tool is appropriate.

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?

Annotations already indicate readOnlyHint=false (write) and destructiveHint=false. The description adds that it creates a draft and does not send, but does not disclose side effects like permissions, idempotency implications, or whether it can be called multiple times per event. 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.

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

Two sentences, no redundancy, front-loaded with action and context. Every sentence adds value.

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?

Description covers what, when, and what-not. With an output schema present, the return format is covered. Minor gap: no explicit prerequisites (e.g., need an inbound message with replyPolicy=suggest), but that is implied by the use case.

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

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

Schema coverage is 100%, so parameters are described in the schema. The description does not add specific parameter semantics beyond what the schema provides, but the overall use case ties them together. 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?

Description clearly states the tool creates a draft reply suggestion that appears inline in the FavCRM Inbox composer, and specifies the exact use case (message.inbound events with replyPolicy='suggest'). It also distinguishes from sending by stating 'does not send anything to the customer.'

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?

Description explicitly states when to use ('for message.inbound events with replyPolicy=suggest') and what it does not do ('does not send anything'). This provides clear usage context, though it lacks an explicit reference to alternatives. Given the sibling list has no direct competitor, the guidance is strong.

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?

Annotations indicate it's not read-only, not idempotent, and not destructive. The description adds that line items are optional and totals are computed server-side. It doesn't mention prerequisites like account existence, but given annotations, the added context 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.

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

The description consists of two concise sentences, front-loaded with the primary action. Every sentence adds value without fluff.

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 create tool with 5 parameters and an output schema, the description covers the essence: creation, optional line items, and returned invoiceId. Minor gaps like prerequisite validation (account existence) are not mentioned, but overall it's complete enough for an agent to understand the tool's function.

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

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

Schema coverage is 100% with descriptions for all parameters. The description adds no new parameter information beyond 'Optionally include line items inline', which matches the schema. Baseline 3 is appropriate as the description does not significantly 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 clearly states the verb 'Create' and the resource 'invoice' for a customer, with optional line items and return value. It effectively distinguishes from other create tools in the sibling list.

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 to create invoices but does not explicitly mention when not to use it or suggest alternatives. It provides a usage hint about optional line items but lacks exclusions or comparisons with related tools like update_invoice (which doesn't exist in siblings).

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

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

Annotations already indicate mutability (readOnlyHint=false). The description adds no further behavioral context such as permissions, rate limits, or side effects. Output schema exists but its content is not described.

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?

Single sentence, front-loaded with action and targets. No redundant or unnecessary words.

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

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

Given the tool's simplicity and presence of output schema, the description is adequate for a basic create operation. Could mention isPinned optionality or note content limits, but not critical.

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 has 100% coverage with descriptions for all parameters. The description reiterates entity types from the schema without adding new meaning. No extra details on isPinned or entityId beyond schema.

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

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

The description clearly states the action 'Add a note' and specifies the target entities: member/account, booking, ticket, or invoice. This distinguishes it from other create tools like create_booking or create_ticket.

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

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

No explicit guidelines on when to use this tool versus alternatives like list_notes or other create tools. Usage is implied for adding notes to supported entities, but no exclusions or context provided.

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

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

Annotations indicate readOnlyHint=false, so the description's "Create" aligns. The addition of "as draft" provides clarity beyond annotations that the rule is not immediately active. No further behavioral details (e.g., permissions, side effects) are disclosed.

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?

Single, front-loaded sentence with no wasted words. Efficiently conveys purpose and key attributes.

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

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

Given the tool's complexity (6 params, nested objects, enums) and presence of an output schema, the description covers the essential creation purpose and draft status. Missing details like what the rule ID is or how to activate, but output schema likely fills gaps.

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

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

Schema coverage is 100% with descriptions for all properties. The description summarizes key parameters (trigger type, conditions, suggested products, discounts) but adds little beyond the schema. 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?

The description clearly states the verb "Create" and the resource "offer rule", specifying it's for upsell/cross-sell and as a draft. It distinguishes from sibling tools like get_offer_rule and list_offer_rules.

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

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

The description implies usage for creating offer rules but does not explicitly state when to use vs alternatives or when not to use. No exclusions or comparative guidance.

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?

Annotations indicate it is a write operation (readOnlyHint=false) and not destructive. The description clarifies the creation purpose and the id parameter's migration use, but does not disclose other behaviors like permission requirements or duplicate handling. With annotations covering the basics, this is adequate.

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

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

The description is two concise sentences, front-loaded with the primary purpose. Every sentence earns its place, with no wasted words.

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

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

Given 10 parameters and an output schema, the description is sparse on overall context (e.g., prerequisites, error conditions). It adequately covers the primary use case but lacks details about common scenarios or company association. Still, it is sufficient for a well-documented parameter set.

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 baseline is 3. The description adds value by explaining the 'id' parameter's legacy migration purpose, reinforcing the schema's description. Other parameters are well-described in schema, but overall the description adds meaningful context.

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

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

The description clearly states the verb 'Create' and the resource 'shop outlet/location'. It also highlights the optional id parameter for legacy migration, which distinguishes it from other create_* tools like create_product or create_service.

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

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

The description does not explicitly state when to use this tool versus alternatives like update_outlet. The mention of optional id for migration provides some context, but there is no guidance on when to choose this tool over siblings.

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

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

The description reveals that the tool creates external Stripe links, which aligns with annotations (readOnlyHint=false, not destructive). It adds context about the link types and the user consent requirement (explicit ask). However, it does not detail post-creation behavior (e.g., whether the user is charged immediately), but annotations already indicate non-idempotent write.

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: first explains functionality concisely with two cases, second gives a crucial usage constraint. No redundant information; each sentence earns its place.

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

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

Given the output schema exists, the description sufficiently covers the core operation and usage condition. It omits edge cases like error handling or missing prerequisites (e.g., need for plan options), but the schema parameter descriptions fill those gaps. Overall adequate for typical agent decision-making.

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

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

Schema coverage is high (80%), and the description does not add significant meaning beyond the schema's parameter descriptions (e.g., 'planId' already suggests using 'list_plan_options'). The description's main value is in purpose/usage, not parameter details; thus a baseline score 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 clearly states the verb 'create' and the specific resources: 'Stripe Checkout link' for new subscriptions and 'Stripe Billing Portal link' for existing ones. It distinguishes this tool from siblings like 'create_subscription' and 'list_plan_options' by focusing on link generation for upgrade/fix billing scenarios.

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

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

The description explicitly states 'Use only after the user explicitly asks to upgrade or fix billing,' providing a clear context for use. While it doesn't name sibling tools as alternatives, the condition effectively guides when to invoke this tool vs. others like 'create_subscription'.

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?

Annotations already indicate it's a mutation (readOnlyHint=false). The description adds useful behavioral details: auto-derivation of excerpt, validation of meta against field schema, and rejection of unknown block types. This goes beyond annotations without contradicting 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 tight three-sentence paragraph. Every sentence earns its place: purpose, prerequisites/alternatives, and special parameter guidance. No filler, front-loaded with the core action.

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

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

Given the tool's complexity (16 parameters, nested blocks) and the presence of an output schema, the description is minimally adequate. It provides high-level guidance but does not cover optional features like tags, categories, or block structure in detail. The schema fills many gaps, so this is acceptable.

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 baseline is 3. The description adds some redundancy (e.g., 'excerpt = plain-text summary only') but no new semantic information beyond what the schema already provides. The prerequisite about post type existence is useful but not a parameter property.

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

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

The description clearly states the tool creates a new CMS post, lists example types (blog_post, page, custom), and distinguishes it from sibling tools like create_post_type. The verb 'create' and resource 'CMS post' are 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 provides clear prerequisites (post type must exist) and names alternatives for discovering or creating post types (list_post_types, create_post_type). It also hints at when to use meta vs excerpt. It does not explicitly say when not to use the tool, but the guidance is strong.

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?

Annotations indicate a write operation (readOnlyHint=false). Description adds behavioral context: fields stored in meta on each post and warns against using excerpt for structured data, which goes beyond annotations.

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 sentences: first states purpose, second gives prerequisite, third gives post-usage and warning. Front-loaded and efficient.

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

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

Given 10 fully described parameters, an output schema, and annotations, the description adequately covers workflow and a common pitfall (excerpt), making it complete for an AI agent.

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

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

Schema coverage is 100%, so the baseline is 3. Description adds value by mentioning slug, label, labelPlural in context, and explains the workflow sequence, justifying a 4.

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

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

The description clearly states it defines a new custom post type with examples like 'treatment' and 'service'. It distinguishes itself from sibling tools like create_post_type_field, which defines field schema.

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?

Explicitly says required before creating posts of that type and directs to use create_post_type_field for structured fields. It does not explicitly state when not to use, but context is clear.

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?

Annotations already indicate non-read-only, non-destructive behavior. Description adds that the field key becomes the meta key, which implies mutation but no further behavioral traits like auth or 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.

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

Three sentences, each adding distinct value. First sentence states purpose, second covers repeater special case, third provides alternative. No unnecessary words.

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

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

For a tool with 9 parameters (3 required) and nested objects, the description covers the main use case and the primary variant (repeater). Does not detail all field types or output, but output schema exists. Adequate for the complexity.

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

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

Schema coverage is 100%, and the description adds value by explaining parameter interactions (e.g., fields required if fieldType=repeater, auto-derivation of key, options format). Goes beyond the schema descriptions.

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

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

Clearly states the verb 'add', resource 'custom field to a post type schema', and explains the meta key behavior. Distinguishes from sibling tools like create_post_type and update_post_type_field.

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

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

Provides specific guidance for using fieldType='repeater' with fields array and advises against storing structured data in excerpt. Could explicitly mention when to use update_post_type_field instead, but still offers clear context.

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

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

Adds context about draft state and merchant activation, which is beyond the annotations. However, no details on side effects, permissions, or what happens during activation. Annotations already indicate non-destructive and non-read-only.

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, no wasted words, front-loaded with the main action and state. Highly concise.

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 a full schema and output schema, the description is functional but could benefit from brief guidance on parameter interdependencies or typical usage. Still adequate for most cases.

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 baseline is 3. Description does not add any additional meaning beyond the schema; no parameter explanations or examples.

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?

Description clearly states verb 'Create', resource 'shop product', and status 'DRAFT', differentiating it from other product-related tools like 'update_product' or 'create_product_category'.

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?

Implies use for creating a draft product but does not explicitly state when to use vs. alternatives or when not to use. No exclusions or prerequisites mentioned.

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

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

Annotations already indicate this is a mutable operation; the description adds minimal behavioral context beyond the basic action, lacking details on side effects, permissions, or constraints.

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, front-loaded with the core purpose, no unnecessary words.

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

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

The description, combined with complete schema and existing output schema, provides adequate context for creating a product category, though it could mention handling of duplicates or defaults.

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

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

Schema coverage is 100%, so baseline is 3. The description highlights parentId usage but does not add significant meaning beyond what the schema descriptions provide.

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

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

The description clearly states the action ('Create a product category') and the resource, and distinguishes from sibling tools like create_category or list_product_categories by specifying the exact entity.

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 some guidance on using parentId for subcategories but does not explicitly compare to other create tools or mention when not to use this tool.

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?

Annotations indicate not read-only or destructive, and the description adds 'Codes are uppercased server-side,' a useful behavioral detail beyond annotations. No contradictions.

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, front-loaded with key info, no wasted words. Efficiently covers main points.

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

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

Given output schema exists, return values are covered. Description covers creation, type, value, and code uppercasing. Could mention other key params like startsAt/endsAt, but not essential for core understanding.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaning to 'value' by explaining the discount string format and mentions type enum values, exceeding schema descriptions.

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

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

The description clearly states 'Create a promotion / discount code' with specific verb and resource. It distinguishes from sibling tools like update_promotion and delete_promotion.

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

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

The description provides clear context for when to use (to create a promotion) but does not explicitly state when not to use or mention alternatives. It references the type and value format, aiding correct usage.

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?

Annotations indicate readOnlyHint=false (modifies state) and destructiveHint=false, which align with the creation action. The description adds that the resource is bookable and for services, but does not discuss side effects like duplicate handling, required permissions, or that the tool is not idempotent. It provides minimal behavioral context beyond the creation fact.

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 conveys the essential purpose and usage context without any wasted words. It is appropriately brief and front-loaded with key information.

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

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

Given the tool's complexity (5 parameters, output schema present, sibling tools like link_resource_to_service), the description is sufficiently complete. It explains the tool's role in creating resources for specific services, and the output schema covers return values. It could mention defaults or linking, but overall it provides adequate context for an AI agent.

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% with descriptions for each parameter. The description does not add any additional meaning beyond the schema; it only gives a general overview of the tool's purpose. Therefore, the baseline score of 3 applies.

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

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

The description clearly states the tool creates a bookable resource with examples (room, equipment, vehicle). It specifies the context of use (services with requiresResource=true), which helps differentiate from general create tools, though it does not explicitly distinguish from siblings like create_service or create_product.

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 indicates the tool is used for creating resources that are linked to services with requiresResource=true, providing a clear usage context. However, it does not mention when not to use this tool (e.g., for services or products) or compare with alternatives like list_resources or link_resource_to_service.

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?

Annotations are minimal (destructiveHint=false, readOnlyHint=false), so description adds value by indicating it's a write operation and differentiating segment types, but lacks detail on side effects or permissions.

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?

Extremely concise: one sentence with a clarifying follow-up. No wasted words, front-loaded with the core action.

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

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

Given the tool's complexity (4 params, nested objects, enums) and presence of output schema, the description is near-complete. It covers the two segment types and purpose, but could mention that 'name' is required or any constraints.

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

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

Schema coverage is 100%, so parameters are documented. The description adds context for segmentType (STATIC/DYNAMIC), but does not elaborate on the complex criteria structure beyond what the schema provides.

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

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

The description clearly states the verb 'Create' and resource 'customer segment', and distinguishes between STATIC and DYNAMIC types, which helps differentiate from siblings like create_account or create_booking.

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

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

Provides explicit guidance on when to use STATIC vs DYNAMIC segment types, offering clear context for tool selection, though it does not explicitly mention when not to use the tool.

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

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

Annotations already indicate the tool is not read-only and not destructive. The description adds no further behavioral context (e.g., validation behavior, side effects of creation). Given annotations cover basic traits, the description's contribution is minimal.

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 two sentences, front-loading the main purpose and adding a helpful tip. No unnecessary words. Excellent conciseness.

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

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

Given the tool's complexity (20 parameters, 2 required) and the presence of an output schema, the description adequately covers the high-level purpose. However, it misses highlighting key constraints like 'allowedTierIds required when visibility=members_only', which are in the schema but could be stressed.

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

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

Schema coverage is 100%, so each parameter has a description. The description mentions 'Sets duration, price, capacity, and policies', which adds slight context but does not significantly augment the schema's detailed parameter explanations.

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

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

The description clearly states 'Create a bookable service' and lists key attributes (duration, price, capacity, policies). It differentiates the tool from other create tools by specifying the resource type, but does not explicitly distinguish from sibling tools like update_service.

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 a valuable prerequisite hint ('Use list_service_categories first if you want to attach to an existing category'), but lacks guidance on when not to use this tool or comparative advice against alternatives like update_service.

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?

Annotations already indicate readOnlyHint=false and destructiveHint=false, so the description's 'Create' is consistent. However, the description adds no extra behavioral context (e.g., side effects, permissions, or uniqueness constraints). It neither contradicts nor significantly supplements annotations.

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, clear sentence that front-loads the action and includes an illustrative example. Every word contributes value; there is no redundancy.

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

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

For a simple creation tool with three parameters (one required) and an output schema, the description adequately explains the purpose and context. It does not discuss return values, but the output schema presumably covers that. It could mention uniqueness or impact on service listing, but is sufficient for practical use.

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 baseline is 3. The tool description provides an example but does not add any semantic information beyond what the schema already provides for each parameter. No additional value.

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 uses a specific verb 'Create' and resource 'service category' with concrete examples ('Treatments', 'Classes'). It clearly distinguishes this from sibling tools like 'create_category' or 'create_product_category' by specifying the domain of bookable services.

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

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

The description implies usage: when you need to group bookable services. It provides clear context but does not explicitly exclude alternatives or state when not to use. Since the purpose is straightforward and distinct from siblings, a score of 4 is appropriate.

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?

Annotations already indicate readOnlyHint=false and destructiveHint=false, so the description only confirms it's a write operation ('Create'). No additional behavioral traits are disclosed (e.g., auth needs, side effects). The description adds little beyond annotations.

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 concise sentences. The first states the purpose, the second provides a key usage tip. No unnecessary words; well-structured.

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

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

Given the tool's complexity (8 parameters, output schema exists), the description is adequate. It covers the main purpose and a key usage pattern. The schema fills in parameter details. Could mention return value but output schema covers that. Adequate for an agent to understand the tool.

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

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

Schema coverage is 100% with descriptions for all parameters. The description adds valuable context on how to use applicableType and applicableItems together, which is not fully covered in the schema descriptions. This enhances understanding of parameter usage.

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

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

The description clearly states it creates a service package/prepaid session bundle. It identifies the resource type and provides a specific configuration hint. However, it does not explicitly distinguish it from sibling tools like create_promotion or create_offer_rule, though the resource type is different.

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 a usage tip (using applicableType=SELECTED with applicableItems) but does not explicitly state when to use this tool over alternatives or when not to use it. No exclusions or comparisons with siblings.

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

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

Annotations indicate readOnlyHint=false and destructiveHint=false, and the description states 'create', which is consistent and implies a write operation with no destructive behavior. However, it does not disclose any additional behavioral traits like idempotency or permission requirements.

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?

Single, front-loaded sentence with no fluff. Every word is necessary to convey the core purpose.

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

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

With 12 parameters and recurring patterns, the description is minimal. While the schema covers details, the description could provide more context on how recurrence settings work, but it is not incomplete.

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 baseline is 3. The description hints at recurrence (weekly/daily) but adds no meaningful explanation of parameters beyond what the schema already provides.

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?

Clearly states the action ('create') and the resource ('bookable schedule window for a service'). Includes specific detail about recurring availability, distinguishing it from sibling tools like list_service_schedules and update_service_schedule.

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 on when to use this tool vs alternatives, such as update_service_schedule or set_resource_availability. No context on prerequisites or typical use cases.

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

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

The description adds no behavioral insights beyond what annotations already provide. Annotations indicate the tool is not read-only (readOnlyHint: false) and not destructive (destructiveHint: false), but the description does not elaborate on side effects (e.g., whether creating a subscription triggers an immediate charge, starts billing, or requires payment method).

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

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

The description is concise and front-loaded with the main action. It consists of two short sentences with no unnecessary words, effectively conveying the essential purpose and flexibility.

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

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

Given the complexity (8 parameters, output schema exists), the description is functional but could be more complete. It covers the two main modes but does not mention defaults (e.g., billingCycle defaults to monthly, autoRenew defaults to true) or that accountId is required. Output schema likely handles return values, so not penalized.

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

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

With 100% schema description coverage, the schema already documents each parameter. The description adds minimal value by summarizing the two modes (tier-based vs custom amount/cycle) but does not provide deeper meaning or relationships between parameters. Baseline 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 clearly states the tool creates a recurring subscription for a member, specifying the key differentiation between binding to a membership tier or setting a custom amount and cycle. This distinguishes it from sibling tools like cancel_subscription, pause_subscription, and resume_subscription, which operate on existing subscriptions.

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

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

The description lacks explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., account must exist, tierId must be valid) or when not to use it (e.g., if updating an existing subscription). No context is provided about choosing between this and other creation tools like create_booking or create_invoice.

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

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

The description indicates the tool creates a survey (mutation), consistent with annotations (readOnlyHint=false). It adds behavioral context about the publishing options, which goes beyond the annotations.

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, well-structured sentence that front-loads the main action and key options. It is efficient but could benefit from a brief mention of required parameters.

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

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

Given the tool has 9 parameters (2 required) and an output schema exists, the description provides sufficient context for the creation action, covering the core functionality and key choices.

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 has 100% coverage with good descriptions for all 9 parameters. The description adds little extra meaning beyond highlighting 'custom question blocks' and the option to publish immediately.

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

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

The description clearly states the action 'Create a survey' and specifies 'with custom question blocks'. It also mentions the ability to publish later or immediately, distinguishing it from other survey tools like list_surveys or update_survey.

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 guidance on when to use this tool by mentioning that you can publish later or set status to published for immediate portal access. It implies the creation context but does not explicitly exclude alternatives like importing a survey.

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?

Annotations indicate this is a write operation (readOnlyHint=false) and not destructive. The description adds 'token-auth' as a behavioral detail, but omits potential side effects, permissions, or idempotency 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?

A single sentence that is front-loaded and concise, but lacks structured breakdown. No extraneous content.

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 9 parameters and an output schema, the description is minimal. It adequately conveys the core purpose but could provide more guidance on recipient identifier selection or invitation behavior.

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

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

Schema coverage is 100%, so the schema already documents all parameters. The description does not add extra meaning beyond the schema, aligning with the baseline score 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 clearly states the action ('Create'), the resource ('token-auth survey invitation'), and the target ('specific member/account or contact'), distinguishing it from sibling tools like create_account or create_contact.

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

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

The description implies usage for creating token-based invitations for specific entities but does not explicitly state when to use this tool versus alternatives or provide context on prerequisites or exclusions.

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?

Annotations already indicate a mutation operation (readOnlyHint=false, destructiveHint=false). The description adds minimal behavioral context beyond the action. It does not disclose side effects, required permissions, or the return value (output schema exists). With annotations, this is adequate but not enhanced.

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 concise sentence with no wasted words. It is front-loaded with the core action. However, it is very brief given the 7 parameters, potentially omitting helpful context.

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 7 parameters, 2 enums, and many siblings. The description fails to explain relationships to other entities (e.g., CRM, team members) or when to use specific parameters. Despite good schema coverage and output schema, the description is too sparse for an agent to fully understand the tool's role in the workflow.

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 explains each parameter. The description adds value by mentioning optional linking to account and assignee, but does not provide syntax or format details beyond the schema. 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?

The description clearly states 'Create a task' which is a specific verb-resource pair. It also mentions optional linking (CRM account, team member), which distinguishes from other create tools. However, it lacks detail on scope (e.g., project context).

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 on when to use this tool versus alternatives like create_note or create_ticket. No mention of prerequisites or typical scenarios. The description is purely declarative without usage context.

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

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

Annotations already indicate non-read-only and non-destructive behavior. Description adds that it generates an invite and a one-time token, plus the verification workflow, which goes beyond annotations.

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, front-loaded with the primary purpose, no unnecessary words. Every sentence earns its place.

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

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

Given output schema exists (so return values documented there), the description adequately covers the workflow and what the tool does. Could mention edge cases but not necessary.

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

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

Schema coverage is 100%, so baseline is 3. Description does not add extra meaning for parameters beyond schema. The output token is mentioned but that is return value, not parameter.

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?

Description clearly states it invites a team member and returns a one-time accept token. Distinguishes from sibling accept tools by mentioning the verification workflow.

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?

Explicitly mentions the subsequent steps (accept_team_invite_request and accept_team_invite_verify), providing clear context for when to use this tool. No exclusions or when-not, but workflow is well described.

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?

Annotations already indicate a write operation (readOnlyHint=false) with no destructive behavior (destructiveHint=false). The description adds no further behavioral context, such as side effects or return value details. It is adequate but not enhanced.

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