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

No annotations provided, so description bears full burden. It discloses that the tool creates an event, attaches to contact/listing, defaults date to now, and lists event types. Does not mention return value or permissions, but these are common for create tools and not egregiously omitted.

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 short sentences, front-loaded with the core purpose. Every sentence adds unique information with no redundancy. Efficient and easy to parse.

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

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

Given the absence of annotations and output schema, the description plus schema provide a solid understanding. It covers the event types, parameter constraints, and a prerequisite step. Missing details like return value or error handling are not critical but would slightly improve completeness.

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 adds value beyond schema: clarifies the 'at least one' constraint for contactId/listingId and advises using find_contacts/find_listings to get IDs. This provides essential usage context not present in 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 the tool's purpose: logging a timeline activity with specific types (phone call, text, etc.). It distinguishes from siblings like delete_timeline_event, list_timeline_events, and create_note by specifying the action and binding to contacts/listings.

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?

Includes explicit guidance to use find_contacts/find_listings first to obtain IDs and to pass at least one of contactId or listingId. However, it lacks differentiation from the sibling tool create_note, which might be confused for note-type timeline events.

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

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

No annotations are provided, so the description must handle disclosure. It describes the toggle behavior but does not mention idempotency, side effects (e.g., notifications), or permissions. The description adequately covers basic behavior but lacks depth.

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 wasted words. Every sentence adds essential information: purpose first, then parameter clarification. Highly efficient.

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

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

For a simple toggle tool with two parameters and no output schema, the description covers the core functionality and provides a usage hint. It could mention the result on success, but the brevity is sufficient given the tool's simplicity.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds value by explaining the default for 'completed' and providing a usage hint for taskId ('from list_tasks').

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: 'Mark a task done (or reopen it).' It specifies the verb (mark done/reopen), the resource (task), and distinguishes from siblings like update_task by focusing specifically on completion status.

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 advises using list_tasks to obtain the taskId and explains the completed parameter (false to reopen). It implies when to use the tool but does not explicitly state when not to use it or compare to update_task.

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

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

No annotations are provided, so the description carries the full burden for behavioral disclosure. It only states 'create a new contact,' implying mutation, but gives no details on side effects, permissions, error states, or uniqueness behavior. This is insufficient for a mutation tool with 14 parameters.

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 long with no extraneous words. It is front-loaded with the core action. However, it could be slightly more structured (e.g., listing key parameters), but overall it is 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 tool has 14 optional parameters, no output schema, and no annotations, the description is too minimal. It does not explain return values, error handling, or constraints (e.g., unique name). The agent lacks enough context to use the tool confidently.

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 43%, meaning 6 of 14 parameters have descriptions in the schema. The tool description adds only that every field is optional and a name is recommended, but does not explain the meaning of the 8 undocumented parameters (e.g., city, state). It compensates slightly but fails to provide meaningful semantics for most 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 'Create a new contact' with a specific verb and resource. It also mentions that all fields are optional but recommends including a name, which distinguishes it from sibling tools like update_contact or search_crm.

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 advises to provide known details and include at least a name, giving basic usage context. However, it lacks explicit when-to-use or when-not-to-use guidance, and does not differentiate from alternatives like update_contact beyond the verb.

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

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

No annotations provided, so description carries full burden. It mentions required fields and default status but does not disclose what the tool returns, side effects, or error scenarios. For a creation tool, important details like ID generation or success response are missing.

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

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

Three tightly packed sentences: purpose, prerequisites, then optional details and default. No wasted words; front-loaded with the most critical 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?

Covers required inputs and default status but omits output format (e.g., does it return the created listing ID?), error handling, or confirmation of success. Given 20 parameters and no output schema, more completeness 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?

Description adds context beyond schema: explains relationship to find_contacts/create_contact for contactId, notes address requirement, and documents default status. Schema coverage is 55% so description complements it well without redundancy.

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 property listing for a client', using a specific verb and resource. It distinguishes from sibling tools like find_listings or update_listing, which have different purposes.

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 prerequisites: 'Requires the owning contactId (use find_contacts, or create_contact for a new client) and a street address.' Also notes default status. While it doesn't explicitly state when not to use, the guidance is clear for a creation 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?

With no annotations, the description must disclose behavior. It states 'save' and encourages liberal use, implying non-destructive creation. However, it omits details like whether notes are appended or overwritten, size limits, or return behavior, which would be helpful for an agent.

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 long, each serving a distinct purpose: stating purpose with examples, encouraging liberal use, and giving a prerequisite. No unnecessary words 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?

Given the simplicity of the tool (2 required params, no output schema), the description covers purpose, parameters with examples, and a prerequisite. It doesn't mention return value or error handling, but for a note creation tool, this is fairly complete.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by giving concrete examples for 'content' (budget, motivation, etc.) and instructing to capture in user's own terms. For 'contactId', it says to use find_contacts, providing practical guidance 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 the tool saves freeform context about a contact, with specific examples (budget/price range, motivation, etc.), distinguishing it from sibling tools like update_contact which handle structured fields.

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

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

The description explains when to use (for unstructured context) and advises using find_contacts first to obtain contactId. It doesn't explicitly state when not to use, but the sibling context (update_contact, list_notes) implies alternatives for structured data or retrieval.

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

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

No annotations are provided, so the description must disclose behavioral traits. It mentions optional contact linking but fails to specify whether the tool is idempotent, what side effects occur, or what the response contains (e.g., no mention of returning the created task ID). This is insufficient for a mutation tool.

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

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

The description is extremely concise with two sentences that capture the core action and a key parameter relationship. No unnecessary words 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?

Given the complexity (6 parameters, no output schema, no annotations), the description is minimal. It misses important details like return value, defaults (priority default is in schema but not description), and behavioral guarantees. However, the sibling tools provide some context for task management workflows.

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 67%, so the schema already describes most parameters (title, dueDate, priority, contactId). The description adds value by hinting that contactId should come from find_contacts, but otherwise provides no additional 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 the action 'Create a task / to-do' with a specific verb and resource. It distinguishes this tool from siblings like update_task and list_tasks by focusing on creation.

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 tasks but does not explicitly state when to use alternatives (e.g., update_task for modifications, complete_task for completion). The hint about contactId from find_contacts provides some guidance, but overall context is lacking.

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

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

No annotations provided, so description must cover behavior. It only implies destruction but does not disclose side effects, reversibility, or permissions needed for deletion.

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 with no wasted words. Purpose is front-loaded, and guidance follows immediately.

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 deletion tool with one param, the description covers what, when, and how to get the ID. It lacks detail on permanence but suffices given the low 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% with description of taskId. The tool description reinforces the schema by mentioning list_tasks, but adds minimal extra 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?

The description clearly states 'Delete a task' as the core purpose, and distinguishes itself from complete_task by specifying when to use delete vs complete.

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 (user asks to remove) and when not to (use complete_task for finishing). Also gives prerequisite of using list_tasks to obtain taskId.

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

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

No annotations are provided, so the description must fully disclose behavioral traits. As a delete operation, it fails to mention that the action is irreversible or destructive, leaving a critical gap in transparency.

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

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

The description is extremely concise with two sentences. The first sentence states the purpose, and the second adds usage and prerequisite guidance. Every word is necessary and front-loaded.

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

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

Given the tool's simplicity (one parameter, no output schema), the description covers purpose, parameter semantics, and usage guidelines. However, it lacks behavioral transparency about destructiveness, which is important for a delete operation, making it slightly 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?

The only parameter, activityId, has a schema description but the tool description adds value by specifying how to obtain it (via find_contacts and list_timeline_events). This context goes beyond what the schema provides, raising the score above baseline 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 'Delete a timeline event' with a specific verb and resource. It distinguishes from siblings like add_timeline_event and list_timeline_events, and provides a context-specific usage hint.

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 gives explicit guidance to 'only delete when the user clearly asks to remove an event' and advises using find_contacts then list_timeline_events to obtain the activityId. This outlines when and how to use the tool, though it does not explicitly state 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?

No annotations are provided, so the description carries the full burden. It describes the full-text search behavior, combinable filters, and return fields. No destructive behavior is implied, which is appropriate for a search tool.

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

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

The description is slightly long but front-loaded with purpose. Each sentence adds value, though minor redundancy exists ('Search or list' vs later 'full-text search'). Overall 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?

For a search tool with 8 parameters and no output schema, the description explains all filters, return fields, and provides usage examples. It is complete enough for an agent to use 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?

Schema description coverage is 100%, but the description adds context: explains query is full-text search, filters can be combined, and lists return fields. It also clarifies the contactId parameter's 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 the tool searches or lists synced emails with multiple filters. It distinguishes from sibling tools like get_email, update_email, delete_email, send_email by mentioning this is a prerequisite for those actions.

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 includes explicit usage examples ('did X email me', 'what's unread in my inbox') and explains that get_email, update_email, delete_email require an emailId from this tool. It doesn't explicitly state when not to use, but the guidance 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?

No annotations provided, so description carries full burden. It explains return fields (ids, owner, key dates) but does not mention pagination, max results, or default ordering. Adequate but incomplete.

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?

Well-structured: main purpose first, then examples, then additional use case. No unnecessary words; 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?

Covers return fields and typical usage patterns. Lacks mention of pagination or sorting, which are common for search tools. Otherwise complete for a search tool with good 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 has 100% parameter descriptions (6/6). Description adds value by showing how to use dateField, dateFrom/dateTo together with examples, and clarifying default for dateField.

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 it searches property listings by address/city/MLS/description, and by filters. Distinguishes from siblings like get_listing (single listing) and create_listing/update_listing (mutation).

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 gives usage scenarios: vague temporal questions (with examples) and obtaining listingId for updates/logging. Tells when to use this tool over 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?

With no annotations provided, the description carries the full burden. It clearly states that the tool reads data (not modifies), and enumerates the types of information returned (fields, notes, tasks, listings, recent timeline). This is transparent for a read-only operation.

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 succinct sentences. It is front-loaded with the core purpose and provides essential usage guidance without any superfluous 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?

Given the tool's simplicity (one parameter, no output schema), the description adequately explains what the tool returns and how to use it. It provides enough context for an agent to select and invoke it 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?

There is only one parameter (contactId) with full schema coverage. The description adds 'Get the contactId from find_contacts,' which slightly supplements the schema's description. This meets the baseline of 3 since the schema already documents the parameter adequately.

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 explicitly states 'Read the full detail of one contact' using a specific verb and resource. It distinguishes itself from sibling tools like create_contact, update_contact, and find_contacts by detailing what is included (fields, notes, tasks, listings, timeline).

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 advises using the tool to 'answer questions about a person or to check what's already recorded before writing,' and directs the user to obtain the contactId from find_contacts. This provides clear context for when to use it, though it does not explicitly mention 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?

With no annotations, the description carries the burden. It accurately describes the read operation and outputs, but does not explicitly state it is read-only or mention any side effects. However, the behavior is clear.

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 the action and scope. Every word adds value, making it efficient and easy to parse.

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

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

Given the tool has no output schema, the description adequately lists the returned data. It could mention that it is a read-only operation, but overall it is complete for its simplicity.

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

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

The sole parameter emailId is fully documented in the schema with a description, and the tool description reinforces that the ID comes from find_emails. Schema coverage is 100%, and the description adds 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 clearly states the tool reads one email in full and lists specific fields (headers, flags, body, contact). It also distinguishes from find_emails, which is a sibling tool that returns metadata.

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 the emailId from find_emails, providing clear context. It does not explicitly mention when not to use this tool, but the purpose is well-defined.

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

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

No annotations are provided, so the description carries the full burden. It labels the action as 'Read' which implies read-only, but does not elaborate on idempotency, authorization needs, or rate limits. Adequate for a simple retrieval tool.

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

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

Two sentences, no filler. First sentence delivers the core purpose and output details. Second sentence provides a critical usage hint. Every word 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 a simple single-parameter tool with no output schema, the description adequately explains return fields. It lacks error handling or edge-case guidance, but is sufficient for typical usage.

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

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

The input schema already describes the parameter with 100% coverage. The description adds value by telling the agent where to obtain the listingId (from find_listings), which aids correct invocation beyond 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 reads a single listing's full detail including property, pricing, owner contact, and timeline. It distinguishes from sibling tools like find_listings (which returns a list) by specifying the scope of data returned.

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 the agent to get the listingId from find_listings, providing a clear usage flow. However, it does not specify when not to use this tool or mention alternatives beyond the implicit sequence.

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?

Describes a read operation but does not disclose behavioral details such as ordering, pagination, or limits. Since there are no annotations, the description carries the full burden but is adequate for a simple list tool.

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

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

Two concise sentences with no extraneous information. Every sentence adds value: action/purpose and prerequisite.

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?

Complete for a simple list tool with a single parameter. The description covers what, why, and prerequisite. No output schema exists, but the return type is implied (list of notes).

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 the single parameter `contactId`, and the description adds no additional semantic 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?

Clearly states the action ('List the saved notes on a contact') and the purpose ('recall context you or the agent captured earlier'). Distinguishes from sibling tools like `create_note` (different action) and `get_contact` (different resource).

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 instructs to use `find_contacts` first to obtain the `contactId`, providing a clear prerequisite and usage pattern.

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

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

No annotations are provided, so the description must disclose behavioral traits. It states the default behavior (returns open tasks only) but omits details like pagination, ordering, rate limits, or that it is a read-only operation. The description adds value but is not fully 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: first defines the tool, second gives filters and examples. No redundant information, every sentence is purposeful.

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 6 parameters, no output schema, and no annotations, the description is reasonably complete: it explains default behavior, common filters, and use cases. However, it lacks mention of sorting, pagination limits, or response format, which would improve completeness.

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 67% of parameters with descriptions. The description adds context by grouping dueAfter/dueBefore as a 'due-date window' and listing filter categories. However, it does not explain each parameter beyond what the schema already provides, so it adds moderate 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 clearly states the tool's purpose (list tasks/to-dos) and distinguishes it from sibling tools like create_task, update_task, complete_task, and delete_task by focusing on listing with filters.

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 explicit usage examples ('what's due this week?' or 'what's open for this client?') and implies when to use the tool, but does not explicitly exclude alternatives or state 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?

No annotations provided, so description carries burden. Mentions 'recent' but doesn't define recency window or ordering. Lacks details on pagination or rate limits, but is a simple list operation.

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 and usage. No extraneous 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?

For a simple list tool with one parameter and no output schema, description adequately explains purpose and prerequisite. Could specify ordering or limit of 'recent' events.

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?

Single parameter contactId has full schema description (100% coverage). Description adds context about using find_contacts first, but no additional parameter semantics 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?

Clearly states the tool lists a contact's recent timeline events with their ids. Distinguishes from sibling tools like delete_timeline_event and add_timeline_event.

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 to call this to get an activityId before editing/deleting, and to use find_contacts first for contactId. Provides good context but no alternatives or 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?

No annotations are provided, so the description must carry the full burden. It discloses that results include linked records (e.g., timeline event with associated contact and listing) and that it is a single call. However, it does not mention whether the operation is read-only, any rate limits, or pagination behavior.

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

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

The description is a single, well-structured paragraph. It front-loads the core functionality in the first sentence and then provides concrete examples. No unnecessary information.

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

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

Given the complexity of 8 parameters and no output schema, the description covers the purpose, cross-record linking, and typical use cases. It lacks information about output format or limits, but the examples and parameter context provide sufficient guidance 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?

The input schema has 100% coverage with descriptions for all 8 parameters. The description adds meaning beyond the schema by explaining how parameters combine (e.g., dateFrom/dateTo with keyword) and providing usage context (e.g., 'query is optional if filtering by date/type').

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 explicitly states that the tool searches across the entire CRM (contacts, listings, tasks, notes, timeline events) in one call, linking results. This clearly differentiates it from sibling tools that operate on single record types (e.g., get_contact, find_listings).

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 concrete use cases ('who did I meet at the open house last weekend', 'what listings does this client have') and implicitly guides away from this tool for dedicated listing date queries by referencing the 'listingDateField' parameter and suggesting 'prefer find_listings'. However, it 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?

Discusses the draft/send behavior and auto-linking to contacts, but does not cover error scenarios, rate limits, or what happens when the account is not connected. Given no annotations, it is adequate but not exhaustive.

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 with clear structure. First sentence provides a high-level summary, followed by details. No fluff, but could be slightly more 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 8 parameters and no output schema, the description covers the main workflow and key behavioral details, but omits return value and error handling. It is moderately complete.

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

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

Schema coverage is 100% (baseline 3). The description adds value by explaining the draft parameter's default and usage, and the format of the 'to' parameter. Other parameters are sufficiently described in 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?

Clearly states it composes an email and either sends or saves as draft. Distinguishes the main action (compose and send/save) but does not differentiate from sibling tools like update_email.

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 clear guidance on when to use draft=true (default) vs false (only when user explicitly asks to send). Mentions prerequisite of a connected email account and references list_email_accounts. Also explains provider-specific behavior for Outlook vs others.

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

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

With no annotations provided, the description carries the full burden. It only hints at partial update semantics ('only include the fields you want to change') but omits other behavioral details such as permissions, idempotency, error handling, or rate limits.

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

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

The description is extremely concise with two sentences, no filler words, and front-loaded with the action and resource. Every sentence contributes meaning.

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 of 15 parameters, low schema coverage, no output schema, and no annotations, the description is adequate but incomplete. It provides the key partial update hint and prerequisite but lacks details on return values, constraints, or potential side effects.

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

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

The description adds value by clarifying the partial update pattern, but with 15 parameters and only 47% schema description coverage, it does not compensate for the lack of descriptions for many parameters (e.g., city, state, zipCode). The hint is useful but insufficient.

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 'Update' and resource 'existing contact', distinguishing it from sibling tools like create_contact and get_contact. It also provides a usage hint regarding partial updates.

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 to 'only include the fields you want to change' and to 'use find_contacts first to get the contactId', providing clear usage context and a prerequisite step. However, it lacks explicit exclusions or when not to use this tool versus 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?

No annotations provided, so the description carries full responsibility. It discloses the mutation behavior (triage actions) and explains that moving to 'trash' removes from inbox. It does not discuss side effects beyond what is implied, but it is sufficiently transparent for a non-destructive update tool.

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

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

The description is three sentences long, front-loaded with the primary purpose, and uses active voice. Every sentence adds value without 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?

Given 7 parameters (1 required) and no output schema, the description covers all actions and provides necessary context for parameter values. It could mention that no return value is expected, but that is 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 coverage is 100% with descriptions for all parameters. The description adds value by explaining the partial update pattern ('Only include the fields you want to change') and providing cross-reference hints (get emailId from find_emails, use trash to remove from inbox).

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 begins with 'Triage an email' and enumerates specific actions (mark read/unread, star/unstar, flag important, move to folder, link/unlink). It clearly identifies the verb 'update' and resource 'email', distinguishing it from siblings like get_email (read-only) and send_email (send).

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 advises to only include fields to change and to get emailId from find_emails. While it does not explicitly list when not to use or compare against siblings, it provides clear guidance for 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?

No annotations provided, so description carries full burden. It implies partial updates ('Only include the fields you want to change') but lacks details on side effects, permissions, or idempotency.

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

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

Two sentences, no fluff, front-loaded with purpose and example.

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 21 parameters and no output schema, the description is too minimal. Missing details on return values, error handling, and exact semantics of status transitions.

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 57%. The description adds limited value beyond schema, mainly emphasizing pipeline status and partial updates. Many parameters have schema descriptions already.

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 'Update' and resource 'listing', with a pipeline example. However, it does not explicitly differentiate from sibling tools like create_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?

Provides explicit guidance to only include changed fields and use find_listings first. No mention of when not to use this tool or alternatives like create_listing.

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

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

No annotations are provided, so the description must disclose behavioral traits. It mentions changing fields but does not describe side effects, permissions, idempotency, or return behavior. For a mutation tool, this is insufficient.

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

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

The description is concise with two sentences: the first lists capabilities, the second provides a usage hint. No unnecessary words 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?

Given no annotations, no output schema, and 7 parameters with moderate schema coverage, the description is decent but incomplete. It implies partial updates but does not explain return values, error handling, or confirm that the behavior matches the implication.

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 description coverage is 43%, with 3 of 7 parameters having descriptions. The description groups parameters by action (e.g., 'reschedule (dueDate)') but does not individually elaborate on all parameters like 'title' or 'description'. It adds some context but does not fully compensate for the missing schema descriptions.

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

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

The description clearly states the tool's purpose: 'Change fields on an existing task' and lists specific actions like reschedule, reprioritize, re-title, recategorize, and relink. It distinguishes itself from siblings like create_task, delete_task, and complete_task.

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 advises to 'Only include what changes' and to 'Use list_tasks to get the taskId', providing clear guidance on when to use the tool. However, it does not explicitly state when not to use it or mention alternatives for marking a task complete.

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