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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the action ('Add a label') and selection methods, but lacks details on permissions needed, rate limits, error handling, or what happens if the label doesn't exist. For a mutation tool with zero annotation coverage, this is 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 a single, efficient sentence that front-loads the core purpose and key usage methods. Every word earns its place with no redundancy or unnecessary elaboration.

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 (6 parameters, mutation operation) and lack of annotations or output schema, the description is minimally adequate. It covers the basic purpose and selection methods but misses behavioral details like side effects or return values, leaving gaps 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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value by mentioning 'IDs or by search query', which aligns with the schema's message_ids and query parameters. Baseline 3 is appropriate when the schema does the heavy lifting.

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 label') and target ('to one or more messages'), distinguishing it from sibling tools like gmail_remove_label_from_messages. However, it doesn't explicitly differentiate from other labeling tools like gmail_create_label or gmail_rename_label, which keeps it from a perfect score.

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 by specifying two methods for selecting messages (IDs or search query), but it doesn't provide explicit guidance on when to use this tool versus alternatives like gmail_mark_as_read_by_ids or gmail_remove_label_from_messages. No exclusions or prerequisites are 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool returns 'email count and list of emails matching that category,' which adds some context about output behavior. However, it lacks critical details: it doesn't specify if this is a read-only operation (implied by 'Get' but not explicit), whether it requires authentication or permissions, any rate limits, or how the list is formatted (e.g., pagination, fields included). For a tool with no annotations, 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 appropriately sized with two sentences that are front-loaded: the first states the purpose, and the second specifies the return values. There's no wasted text, and it efficiently conveys core information. However, it could be slightly more structured by explicitly separating purpose from behavior, but it's still concise 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 tool has one parameter with full schema coverage and no output schema, the description is moderately complete. It covers the basic purpose and return values, but lacks depth: it doesn't explain the category semantics, authentication needs, or error handling. For a simple read operation, this is adequate but has clear gaps, especially in behavioral context due to missing annotations.

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

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

Schema description coverage is 100%, with the schema fully documenting the single parameter 'category' and its allowed values. The description adds no additional meaning beyond what the schema provides—it doesn't explain the semantics of categories (e.g., what 'navy' or 'action_required' mean) or provide usage examples. With high schema coverage, the baseline is 3, as the description doesn't compensate but doesn't detract either.

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: 'Get a summary of unread emails in one specific category.' It specifies the verb ('Get a summary') and resource ('unread emails in one specific category'), and distinguishes it from siblings like 'gmail_list_unread' by focusing on categorization. However, it doesn't explicitly differentiate from 'gmail_get_categories' (which might list categories) or 'gmail_daily_summary' (which might summarize by time), so it's not fully sibling-aware.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose this over 'gmail_list_unread' (which lists all unread emails) or 'gmail_get_categories' (which might provide category information). There's no context about prerequisites, such as needing unread emails in the specified category, or exclusions. Usage is implied by the purpose but not explicitly 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?

With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool creates a new label and returns an ID, but lacks critical details: it doesn't mention authentication requirements, rate limits, error conditions (e.g., duplicate label names), or whether the operation is idempotent. For a mutation tool with zero annotation coverage, this is 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 a single, efficient sentence that front-loads the core purpose ('Create a new Gmail label') and includes key details (optional colors, return value) without any wasted words. Every part earns its place by adding 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?

Given this is a mutation tool with no annotations and no output schema, the description is incomplete. It mentions the return value (ID) but lacks other critical context: authentication needs, error handling, or behavioral traits like idempotency. For a tool that modifies Gmail state, this leaves significant gaps 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 description coverage is 100%, so the schema already fully documents all three parameters (label_name, background_color, text_color) with descriptions and optionality. The description adds no additional parameter semantics beyond what's in the schema, such as format examples or constraints, so it meets 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 new Gmail label') and resource ('Gmail label'), distinguishing it from siblings like gmail_list_labels (read) or gmail_delete_label (delete). It also mentions the optional feature of custom colors, adding specificity beyond just the basic creation function.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing authentication), compare it to similar tools like gmail_rename_label for modifying existing labels, or specify scenarios where creating a label is appropriate versus unnecessary.

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 of behavioral disclosure. It mentions 'shows unread counts and top emails' but doesn't specify what 'top emails' means (e.g., by recency, importance), whether this is a read-only operation, if it requires authentication, or any rate limits. For a tool that processes email data, this leaves critical behavioral aspects undocumented.

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, stating the core purpose in the first sentence. The second sentence adds useful detail about the summary content. Both sentences earn their place by clarifying the tool's output, though it could be slightly more structured (e.g., explicitly separating purpose from features).

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 email summarization, no annotations, and no output schema, the description is incomplete. It doesn't explain the return format (e.g., structured data vs. text), how categories are determined, or what 'top emails' entails. For a tool with behavioral nuances and no structured output documentation, this leaves significant gaps for the 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 description coverage is 100%, so the schema fully documents both parameters (hours and include_read). The description adds no parameter-specific information beyond what's in the schema, such as how hours affects categorization or the implications of include_read. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't 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 tool's purpose: 'Generate a summary of recent emails organized by category' with specific categories listed (Navy, Kids, Financial, Action Items). It distinguishes from siblings like gmail_list_unread or gmail_inbox_stats by focusing on categorized summaries rather than raw lists or statistics. However, it doesn't explicitly differentiate from gmail_category_summary, which appears similar.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose this over gmail_category_summary, gmail_inbox_stats, or gmail_list_unread, nor does it specify prerequisites or exclusions. The lack of usage context leaves the agent guessing about appropriate scenarios.

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 of behavioral disclosure. It adds useful context beyond the schema by stating the tool cannot delete system labels and requires confirmation, which are behavioral traits. However, it does not cover other aspects like error handling, permissions needed, or what happens on deletion (e.g., if messages lose the label).

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 front-loaded with the core purpose in the first sentence, followed by two concise constraints. Every sentence earns its place by adding critical information (deletion action, system label restriction, confirmation need) without redundancy or 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?

Given no annotations and no output schema, the description is moderately complete for a destructive tool. It covers the action, constraints, and safety mechanism, but lacks details on return values, error cases, or side effects (e.g., impact on labeled messages). For a deletion tool with 3 parameters, this leaves some gaps in contextual 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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by implying the 'confirm' parameter is for safety, but does not provide additional semantics like format examples or edge cases. Baseline 3 is appropriate as the schema does the heavy lifting.

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 ('Delete a Gmail label') and resource ('by name or ID'), distinguishing it from siblings like 'gmail_rename_label' or 'gmail_create_label'. It explicitly mentions constraints ('Cannot delete system labels') that differentiate its scope from other label-related tools.

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 delete labels) and when not to (for system labels), but does not explicitly name alternatives like 'gmail_rename_label' or 'gmail_remove_label_from_messages' for different operations. It implies usage through the confirmation requirement but lacks explicit comparison to 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?

With no annotations provided, the description carries full burden. It describes what the tool does (list categories and rules) but lacks behavioral details like whether this requires authentication, if it's a read-only operation, rate limits, or what format the output takes. It doesn't contradict annotations, but provides 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 is two concise sentences that efficiently convey the tool's purpose. The first sentence states the core function, and the second elaborates on what it shows. Every word earns its place with no redundancy or 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 tool with 0 parameters and no output schema, the description adequately explains what it does. However, without annotations or output schema, it lacks details about return format, authentication needs, or error handling. It's complete enough for basic understanding but misses advanced contextual information.

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 tool has 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description doesn't discuss parameters, which is appropriate. Baseline for 0 parameters is 4, as it doesn't need to compensate for any gaps.

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 with specific verbs ('List', 'Shows') and resources ('configured email categories and their matching rules', 'how emails are automatically categorized'). It distinguishes from siblings like gmail_list_labels (which lists labels) and gmail_category_summary (which might summarize categories differently).

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 understanding email categorization rules, but doesn't explicitly state when to use this tool versus alternatives like gmail_category_summary or gmail_get_priorities. No exclusions or prerequisites are mentioned, leaving usage context somewhat vague.

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 discloses the tool's read-only nature by stating 'Get' and listing return fields, but it doesn't mention behavioral traits like error handling (e.g., invalid IDs), authentication needs, rate limits, or whether it retrieves attachments. The description adds some context but leaves gaps for a tool with no annotation coverage.

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 front-loaded with the core purpose in the first sentence and efficiently lists return fields in the second. Every sentence earns its place by adding critical information without redundancy, making it appropriately sized 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 no annotations and no output schema, the description is moderately complete for a simple read operation. It covers the purpose, parameter semantics, and return fields, but lacks details on error cases, authentication, or behavioral nuances. For a tool with 1 parameter and no complex outputs, it's adequate but has clear gaps in transparency.

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 1 parameter with 100% coverage, providing a clear description. The description adds value by specifying that the email_id is 'obtained from search or list results,' which clarifies its source beyond the schema's technical definition. This compensates well, though it doesn't detail format constraints beyond what's implied.

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 ('Get the full content'), resource ('a specific email'), and key identifier ('by its Gmail message ID'). It distinguishes from siblings like gmail_search (which finds emails) and gmail_list_unread (which lists emails) by focusing on retrieving detailed content for a single identified message.

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 detailed email content for a known message ID, but it doesn't explicitly state when to use this versus alternatives like gmail_search (which might return summaries) or prerequisites like needing the ID from another tool. It provides basic context but lacks explicit guidance on exclusions or named 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 of behavioral disclosure. It usefully adds that the tool 'Always includes read emails since you want to track all pending deliveries,' which clarifies scope beyond what the parameter schema indicates. However, it doesn't mention other important behaviors like rate limits, authentication needs, or what happens if no emails are found, leaving gaps for a mutation-free 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 efficiently structured in two sentences: the first states the core purpose, and the second adds crucial behavioral context about including read emails. Every sentence earns its place with no wasted words, making it easy to parse 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?

For a simple read-only tool with one well-documented parameter and no output schema, the description is mostly complete. It clearly explains what the tool does and includes important behavioral context (including read emails). The main gap is lack of output format details, which would be helpful since there's no output schema, but this is partially mitigated by the tool's straightforward purpose.

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 for its single parameter (days_back), so the schema already fully documents it. The description doesn't add any parameter-specific information beyond what's in the schema, such as format details or examples. This meets the baseline of 3 when schema coverage is high.

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 with specific verbs ('Get package delivery and shipping notification emails') and resources ('emails from Amazon, UPS, FedEx, USPS, and other carriers'). It distinguishes itself from siblings like gmail_search or gmail_get_email by focusing exclusively on package-related emails with tracking info, not general email retrieval.

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 this tool: to find package tracking emails from specific carriers. It implies an alternative to general search tools by specifying this specialized focus. However, it doesn't explicitly state when NOT to use it or name specific sibling alternatives, which prevents a perfect score.

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 of behavioral disclosure. It describes what the tool does (searches for priority emails with specific criteria) and mentions automatic exclusion of routine items, which is useful behavioral context. However, it doesn't disclose important behavioral aspects like whether this requires specific permissions, rate limits, or what the response format looks like.

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 efficiently structured in two sentences that each earn their place. The first sentence states the core purpose and configuration source, while the second provides important behavioral details about search criteria and exclusions. No wasted words or redundant 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 tool with 2 parameters, 100% schema coverage, but no annotations and no output schema, the description provides adequate context about what the tool does and its search criteria. However, it doesn't describe the return format or structure of results, which would be important for an email retrieval tool. The description is complete enough for basic understanding but lacks output details.

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 fully documents both parameters (days_back and include_read). The description doesn't add any parameter-specific information beyond what's in the schema. The baseline score of 3 is appropriate when the schema does all the parameter documentation work.

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 with specific verb ('Get priority emails') and resource ('based on the known_priorities category in categories.yaml'), and distinguishes it from siblings by specifying it searches for emails matching configured senders and subjects while automatically excluding routine items. This is more specific than generic search tools like gmail_search.

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 about when to use this tool - for finding priority emails based on configured categories, senders, and subjects. It distinguishes from generic search by mentioning the automatic exclusion of routine items. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what data is returned but doesn't describe how it behaves: e.g., whether it requires specific permissions, if it's a read-only operation (implied by 'get' but not explicit), potential rate limits, data freshness (real-time or cached), or error conditions. The description adds minimal context beyond the basic output metrics.

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, efficient sentence that front-loads the core purpose ('Get current inbox statistics') and then lists the specific metrics. Every word earns its place with no redundancy or unnecessary details, making it easy to scan and understand quickly.

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 low complexity (0 parameters, no annotations, no output schema), the description is minimally adequate. It explains what the tool returns but lacks details on behavioral aspects like permissions, rate limits, or data sourcing. For a simple read operation, this might suffice, but the absence of annotations means the description should ideally cover more operational context to be fully 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 input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, focusing instead on the output semantics. This meets the baseline for tools with no parameters, as there's nothing to compensate for.

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: 'Get current inbox statistics' with specific metrics listed (total messages, unread count, starred count, important message count). It distinguishes itself from siblings like gmail_list_unread or gmail_get_priorities by focusing on aggregated statistics rather than listing or retrieving specific emails. However, it doesn't explicitly contrast with all siblings (e.g., gmail_category_summary might overlap in summarizing data).

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., authentication), timing considerations (e.g., real-time vs cached data), or compare it to siblings like gmail_daily_summary or gmail_get_categories that might provide related summary information. Usage is implied by the purpose but not explicitly 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?

With no annotations provided, the description carries the full burden. It discloses the return format ('label names and IDs') and scope of labels included, which is helpful behavioral context. However, it lacks details on permissions needed, rate limits, pagination, or error handling, leaving gaps for a read 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 is a single, well-structured sentence that efficiently conveys purpose, scope, and return values without any wasted words. It is front-loaded with the core action and maintains clarity throughout.

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 (0 parameters, no output schema, no annotations), the description is largely complete—it explains what the tool does, what it returns, and the label types included. However, it could benefit from mentioning any limitations (e.g., label count constraints) to achieve full 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 tool has 0 parameters with 100% schema description coverage, so the schema fully documents the lack of inputs. The description adds no parameter information, which is appropriate here, earning a baseline score above 3 due to the zero-parameter scenario.

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 ('List all Gmail labels') and distinguishes what it includes ('both system labels... and user-created labels'), differentiating it from siblings like gmail_get_categories or gmail_list_unread. It specifies the resource (Gmail labels) with scope details.

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 retrieving all labels, but provides no explicit guidance on when to use this tool versus alternatives like gmail_get_categories or gmail_search. There's no mention of prerequisites, exclusions, or specific contexts where this tool is preferred.

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 full burden but only states what the tool does, not behavioral traits like whether it's read-only, requires authentication, has rate limits, or returns paginated results. It mentions 'pre-configured categories' but doesn't explain how these are set up or their impact.

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 with zero waste. The first sentence states the core purpose, and the second adds optional functionality. It's front-loaded and appropriately sized for a simple listing tool.

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 read operation with 2 parameters and 100% schema coverage but no output schema or annotations, the description is minimally adequate. It covers what the tool does but lacks context about return format, error handling, or behavioral constraints that would be helpful for an 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 description coverage is 100%, so the schema already fully documents both parameters. The description adds marginal value by mentioning 'pre-configured category' and listing examples, but doesn't provide additional semantics beyond what's in the schema descriptions. Baseline 3 is appropriate when schema does the heavy lifting.

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 ('List') and resource ('unread emails from the inbox'), making the purpose immediately understandable. It distinguishes from siblings like 'gmail_search' by focusing specifically on unread emails, though it doesn't explicitly contrast with 'gmail_get_priorities' or 'gmail_inbox_stats' which might also involve email retrieval.

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 listing unread emails with optional category filtering, but provides no explicit guidance on when to use this tool versus alternatives like 'gmail_search' or 'gmail_get_priorities'. It mentions categories but doesn't explain when to filter by them versus using other 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context about the confirmation requirement and preview capability (via confirm=false), which are not obvious from the schema alone. However, it does not cover other behavioral aspects like permissions needed, rate limits, or what happens on success/failure, leaving gaps 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 two sentences, front-loaded with the core purpose and followed by a crucial behavioral note. Every word earns its place with zero waste, making it highly 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?

For a mutation tool with no annotations and no output schema, the description is adequate but incomplete. It covers the purpose and confirmation behavior but lacks details on permissions, error handling, or return values. Given the complexity (modifying email states), more context would be beneficial for safe 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?

Schema description coverage is 100%, so the schema already fully documents both parameters (message_ids and confirm). The description does not add any additional semantic meaning beyond what the schema provides, such as format examples or edge cases. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Mark specific emails as read') and the resource ('using their message IDs'), distinguishing it from sibling tools like 'gmail_mark_as_read_by_query' (which uses queries) and 'gmail_mark_as_unread_by_ids' (which does the opposite). It precisely conveys the verb+resource combination.

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 usage by stating 'Requires confirmation to execute,' which implies a prerequisite (setting confirm=true). However, it does not explicitly mention when to use this tool versus alternatives like 'gmail_mark_as_read_by_query' or 'gmail_mark_as_unread_by_ids,' so it lacks explicit sibling differentiation.

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 of behavioral disclosure. It mentions the confirmation requirement ('Requires confirmation'), which is a critical safety feature for a mutation tool. However, it doesn't disclose other important behaviors like whether the operation is reversible, what permissions are needed, rate limits, or what happens on success/failure. The description adds some value but leaves significant gaps.

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 perfectly concise with just two sentences that each earn their place. The first sentence states the core purpose, and the second adds critical behavioral context (confirmation requirement). There's zero wasted language, and the information is front-loaded appropriately.

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 this is a mutation tool with no annotations and no output schema, the description should do more to be complete. While it covers the basic purpose and confirmation requirement, it lacks information about what the tool returns, error conditions, side effects, or detailed behavioral constraints. The description is adequate but has clear gaps for a tool that modifies email state.

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

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

Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds no additional parameter information beyond what's in the schema. According to the scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no param info in the description, which applies here.

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 ('mark as read') and target resource ('emails matching a search query'), distinguishing it from siblings like gmail_mark_as_read_by_ids (which uses IDs instead of queries) and gmail_mark_as_unread_by_query (which performs the opposite action). The verb+resource combination is precise and unambiguous.

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 this tool ('mark emails matching a search query as read') and mentions the 'Requires confirmation' prerequisite. However, it doesn't explicitly state when NOT to use it or name alternatives like gmail_mark_as_read_by_ids for ID-based operations, which would be helpful for sibling differentiation.

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 of behavioral disclosure. It adds value by stating the confirmation requirement, which hints at a safety mechanism, but lacks details on permissions, rate limits, or what happens if IDs are invalid. It doesn't contradict annotations, but more behavioral context would be helpful 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 front-loaded with the core purpose in the first sentence and adds a crucial behavioral note in the second. Both sentences earn their place by providing essential information without redundancy, making it efficient 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 (a mutation operation with 2 required parameters) and no annotations or output schema, the description is adequate but has gaps. It covers the action and a key behavioral trait (confirmation), but lacks details on error handling, return values, or integration with sibling tools, which could 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 description coverage is 100%, so the input schema fully documents both parameters (message_ids and confirm). The description doesn't add any additional meaning beyond what the schema provides, such as format examples or edge cases. Baseline 3 is appropriate as the schema handles the heavy lifting.

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 ('Mark specific emails as unread') and the resource ('using their message IDs'), distinguishing it from siblings like gmail_mark_as_unread_by_query which uses queries instead of IDs. The verb+resource combination is precise and unambiguous.

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 by specifying 'Requires confirmation to execute,' which indicates a prerequisite for use. However, it doesn't explicitly differentiate when to use this tool versus alternatives like gmail_mark_as_unread_by_query or gmail_mark_as_read_by_ids, leaving some ambiguity in sibling 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the confirmation requirement, which is useful context, but lacks details on permissions, rate limits, or what happens to emails (e.g., if it affects all matching emails up to max_emails). It doesn't contradict annotations, but could be more informative.

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 core purpose and followed by essential usage guidance. Every word earns its place, with no redundancy or fluff, making it highly 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?

For a mutation tool with no annotations and no output schema, the description is adequate but has gaps. It covers the purpose and confirmation need, but lacks details on behavioral aspects like error handling or return values. Given the complexity and lack of structured data, it's minimally viable but not fully comprehensive.

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

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

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema, such as explaining Gmail query syntax further or elaborating on the confirmation logic. Baseline 3 is appropriate given high schema 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 clearly states the specific action ('mark emails matching a search query as unread'), identifies the resource (emails), and distinguishes it from siblings like 'gmail_mark_as_unread_by_ids' by specifying the query-based approach. It's precise and avoids tautology.

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 this tool (to mark emails as unread based on a search query) and mentions a prerequisite ('Requires confirmation'), but it doesn't explicitly state when not to use it or name alternatives like 'gmail_mark_as_unread_by_ids' for ID-based operations.

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

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

No annotations are provided, so the description carries full burden. It mentions the action ('remove') and optional preview mode via 'confirm', but doesn't disclose behavioral traits like required permissions, rate limits, whether removal is reversible, effects on message organization, or error handling. For a mutation tool with zero annotation coverage, this is 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 appropriately sized with two sentences that are front-loaded with the core purpose. Every sentence earns its place by covering the action and target methods, though it could be slightly more structured (e.g., explicitly listing parameters). No wasted words or 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 6 parameters with full schema coverage but no annotations or output schema, the description is minimally complete. It covers the what and how but lacks context on behavioral aspects (e.g., safety, side effects) and doesn't explain return values. For a mutation tool, this leaves gaps that could hinder agent 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 description coverage is 100%, so the schema fully documents all 6 parameters. The description adds minimal value beyond the schema, only implying parameter usage ('Can specify messages by IDs or by search query') without explaining semantics like label_name/label_id exclusivity or query syntax. Baseline 3 is appropriate when schema does the heavy lifting.

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 ('remove') and resource ('a label from one or more messages'), distinguishing it from siblings like gmail_add_label_to_messages (adds label) and gmail_delete_label (deletes label entirely). It specifies the operation's scope with 'one or more messages' and identifies target selection methods.

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 by mentioning alternative methods (IDs vs. query) but doesn't explicitly state when to use this tool versus alternatives like gmail_remove_label_from_messages (no direct alternative for removal) or differentiate from gmail_mark_as_read/unread operations. It lacks guidance on prerequisites, error conditions, or integration with 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds some context by specifying the system label constraint, but does not cover other behavioral aspects like permissions needed, error handling, or what happens if the new name conflicts. It adequately describes the mutation nature but lacks depth for a tool with no annotation support.

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, efficient sentence that is front-loaded with the core purpose and includes a critical constraint. There is no wasted language, and every word earns its place, 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 moderate complexity (mutation with 3 parameters), no annotations, and no output schema, the description is minimally adequate. It covers the purpose and a key constraint but lacks details on behavioral traits, error cases, or return values, leaving gaps for an agent to operate effectively.

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

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

Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description does not add any additional meaning beyond what the schema provides, such as format details or examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Rename') and resource ('an existing Gmail label'), and distinguishes it from siblings by specifying it cannot rename system labels. It precisely identifies what the tool does without being vague or tautological.

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 by stating 'Cannot rename system labels,' which implicitly guides when not to use it. However, it does not explicitly mention when to use this tool versus alternatives like gmail_create_label or gmail_delete_label, or provide prerequisites beyond the system label restriction.

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 discloses that the tool returns a list of emails with specific fields (subject, sender, date, snippet) and mentions Gmail search operators, which adds useful context. However, it lacks details on permissions needed, rate limits, pagination, or error handling for a search 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 is appropriately sized and front-loaded, with two sentences that efficiently convey purpose, return value, and usage examples without unnecessary details. Every sentence earns its place by providing essential 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 moderate complexity (search with two parameters), no annotations, and no output schema, the description is mostly complete. It covers purpose, usage, and return fields, but could improve by addressing behavioral aspects like permissions or limitations. It compensates well for the lack of structured data.

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 fully documents the two parameters (query and max_results). The description adds minimal value beyond the schema by mentioning Gmail search operators, which are implied in the schema's examples. Baseline score of 3 is appropriate as the schema does the heavy lifting.

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 with specific verb ('Search') and resource ('emails'), and distinguishes it from siblings by focusing on search functionality rather than labeling, reading, sending, or other operations. It explicitly mentions what it returns (list of matching emails with specific 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 provides clear context for when to use this tool (searching emails with Gmail query syntax) and includes examples of search operators. However, it does not explicitly state when not to use it or name specific alternatives among the sibling tools (e.g., gmail_list_unread for a simpler unread list).

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 of behavioral disclosure. It adds valuable context: 'Requires confirmation before sending' indicates a safety mechanism, and 'Can send new emails or reply to existing threads' clarifies functionality. However, it misses details like rate limits, authentication needs, error handling, or what happens on failure. For a mutation tool with zero annotation coverage, this is a moderate but incomplete effort.

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: two sentences that directly state the purpose and a key behavioral trait. Every sentence earns its place by adding value, with no redundant or vague language. It could be slightly more structured (e.g., separating functionality and requirements), but it's efficient overall.

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 (a mutation tool for sending emails with 7 parameters), no annotations, and no output schema, the description is moderately complete. It covers the basic purpose and a confirmation requirement but lacks details on return values, error cases, or advanced usage. For a tool with this level of responsibility, more context would be beneficial to fully guide an 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% description coverage, so parameters like 'to', 'subject', 'body', etc., are well-documented in the schema. The description adds no additional parameter semantics beyond what the schema provides (e.g., no extra syntax or format details). According to the rules, with high schema coverage, the baseline is 3 even with no param info in the 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 tool's purpose: 'Send an email. Can send new emails or reply to existing threads.' It specifies the verb ('send') and resource ('email'), distinguishing it from sibling tools like labeling, searching, or reading operations. However, it doesn't explicitly differentiate from hypothetical similar tools (e.g., 'send_email_with_attachments'), which keeps it from a perfect score.

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 usage context by mentioning 'Can send new emails or reply to existing threads,' which implies when to use it for different scenarios. However, it lacks explicit guidance on when to choose this tool over alternatives (e.g., vs. other email-sending tools if they existed) or any prerequisites beyond confirmation. No exclusions or clear alternatives are named, making it implied rather than explicit.

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