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

The description does not disclose side effects (e.g., whether the message is removed from the original mailbox), required permissions, or idempotency. Since no annotations are provided, the description carries the full burden and fails to convey behavioral traits.

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

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

While the description is very short (one sentence), it is under-specified and lacks essential information. Conciseness should not come at the expense of completeness; key details about parameters and behavior are missing.

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 two undocumented parameters, the description is severely incomplete. The agent lacks critical information to use this tool correctly, such as parameter semantics and 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 input schema has 0% description coverage, and the tool description provides no explanation of the 'mailbox' or 'uid' parameters. The agent receives no help understanding what values to use or their format.

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 (move a message to Archive mailbox) and identifies the resource (message) and destination (Archive mailbox). However, it does not distinguish this from sibling tool 'move_message', which could also move to the Archive mailbox.

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

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

No guidance is provided on when to use this tool versus alternatives like 'move_message' or 'delete_message'. The description lacks context about prerequisites or 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?

Description discloses no side effects (doesn't send or save) but lacks details on return value format and any limitations. Without annotations, more behavioral context (e.g., how preview is returned) would improve transparency.

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

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

Three sentences, front-loaded with purpose and key constraint (does not send), no wasted words.

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

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

For a tool with 9 parameters and no output schema, the description is minimal. It doesn't specify how the preview is returned or guide parameter usage (e.g., html vs text). More detail would increase 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 44%, and description adds no further parameter explanation beyond what schema provides. For the described parameters, it adds no new meaning; for undocumented parameters, it offers no guidance.

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?

Title and description clearly state the tool builds an email for review and does not send. It uses a specific verb 'build' and resource 'email', and contrasts with sibling 'send_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?

Explicitly says 'Does not send or save anything' and 'Use this first, then send_email after the user approves', providing clear when-to-use and when-not-to-use guidance.

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

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

The description reveals that the tool has two behaviors depending on message state (move to trash or expunge). However, no annotations exist, and it does not disclose permissions, side effects, or reversibility details.

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

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

A single sentence that efficiently conveys the core action. No unnecessary words, but could benefit from expanded context.

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

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

Lacks information about return values, error conditions, or any post-action state. For a tool with no output schema, the description should provide more 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 0%, and the description does not explain what 'mailbox' or 'uid' represent. Parameter semantics are entirely absent beyond the schema field names.

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 moves a message to Trash or expunges it if already in Trash. It distinguishes from sibling tools like 'archive_message' by specifying destructive action.

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

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

No guidance on when to use this tool versus alternatives like 'archive_message' or 'move_message'. The description lacks context for decision-making.

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 discloses the key behavior (saving to a temp file and returning path) but omits details on temp file lifecycle, permission requirements, or error handling.

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

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

Two sentences, no wasted words, essential information front-loaded. Every sentence earns its place.

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

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

No output schema, so description should cover return value; it says 'return its path' but lacks format/type details. No mention of failure scenarios. Adequate for basic use but leaves gaps.

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

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

Schema description coverage is only 33% (only attachmentId has a description). The description adds meaning for attachmentId (source from get_message) but provides no additional info for mailbox or uid, leaving them underspecified.

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

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

The description uses specific verb 'save' and resource 'attachment', clearly states the output (path), and references the source of attachmentId. It is distinct from sibling tools as no other tool handles attachment downloads.

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 implicitly suggests retrieving attachmentId from get_message, providing a usage hint. However, it does not explicitly state when to use this tool vs alternatives, but no alternatives exist among 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?

No annotations are provided, so the description carries full burden. It discloses that the tool requires user approval before calling, but it does not specify side effects such as whether the message is actually sent or if the original message is marked as forwarded. This is minimally adequate 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?

The description is extremely concise with two short sentences. The first sentence states the core purpose, and the second provides a critical constraint. No unnecessary words are present.

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 lack of annotations, output schema, and limited parameter coverage, the description is incomplete. It does not mention return values, prerequisites (e.g., that the message must be fetched or that uid and mailbox are required), error conditions, or what happens after forwarding (e.g., sends immediately vs. drafts).

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

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

With only 20% schema description coverage (only the 'note' parameter has a description), the description adds no explanation for parameters like mailbox, uid, to, or cc. The description text does not define these fields, making it difficult for an agent to provide correct values.

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 ('Forward an existing message to new recipients'), which is a specific verb+resource combination. It effectively distinguishes itself from sibling tools like reply, send_email, and save_draft by specifying that it forwards an already existing 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 includes a critical usage guideline: 'Only call after explicit user approval.' However, it does not provide any context about when to use this tool versus alternatives (e.g., when to forward vs. reply or send as new email), which limits its helpfulness for 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?

No annotations provided, so description must disclose behavior. It states what is fetched but not side effects, safety (read-only), or rate limits. Adequate but could be more transparent.

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

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

Single sentence, concise, front-loaded with verb and resource. No wasted words.

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

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

For a simple fetch tool with 2 parameters and no output schema, the description adequately covers purpose and scope. Could mention return format or permissions, but not critical.

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

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

Schema coverage is 100% with clear parameter descriptions. Description adds no extra semantic value beyond schema; baseline 3 is appropriate.

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

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

Description clearly states the verb 'Fetch' and resource 'full message' with explicit components (headers, text+HTML body, attachment metadata). Distinguishes from sibling tools like get_thread or list_mailboxes.

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

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

No explicit when-to-use or alternatives guidance. The purpose implies usage for retrieving full message content, but lacks contrast with sibling tools like get_thread or search_messages.

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

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

The description reveals the ordering behavior ('ordered oldest to newest') but does not disclose whether the operation is read-only, whether it includes the original message, or any side effects. With no annotations, more behavioral context is needed.

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

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

Single sentence, no wasted words. However, given the lack of other structured information, the description could be slightly expanded without losing conciseness.

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

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

With no output schema, no annotations, and no parameter descriptions, the description is incomplete. It does not explain return format, error cases, or how the parameters relate to the thread retrieval.

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 0% and the description does not explain what 'mailbox' or 'uid' represent. The description adds no meaning beyond the parameter names, leaving the agent to infer their purpose.

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 verb 'Fetch', the resource 'conversation a message belongs to', and the ordering 'oldest to newest'. It distinguishes from sibling tools like get_message (which fetches a single message) by implying the tool retrieves the full thread.

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

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

No guidance on when to use this tool versus alternatives (e.g., get_message for single messages, search_messages for finding messages). No prerequisites or exclusions 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 full burden for behavioral disclosure. It only states the basic purpose without revealing details such as whether the operation is read-only, any authentication requirements, or the response format. The description lacks sufficient 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 a single, focused sentence that conveys the essential purpose without any unnecessary words or redundancy. It is 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 zero parameters and no output schema, the description is reasonably complete. It specifies what the list includes (IMAP paths and roles). However, it could briefly mention the typical use case (e.g., for folder navigation) or return structure, but overall it covers the core.

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 no parameters, and schema description coverage is 100% (since there are none). Per guidelines, baseline is 4 for zero parameters. The description adds no additional parameter information, which is acceptable as there are none to document.

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 lists all mailboxes/folders with IMAP paths and roles. It uses a specific verb 'List' and resource 'mailboxes/folders', and adds details about the output (IMAP paths, roles). This distinguishes it from sibling tools which focus on message operations.

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

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

The description does not provide explicit guidance on when to use this tool versus alternatives. However, context with sibling tools (all message operations) implies it is the only tool for listing mailbox structure. No when-not-to-use or prerequisite information is given.

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. Only states basic action without disclosing side effects, permissions, or error conditions. Lacks behavioral 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?

Extremely concise but under-specified. One sentence provides bare minimum, lacking necessary detail for effective tool usage.

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 3 required parameters with no schema descriptions or output schema, the description fails to provide sufficient information for an agent to use the tool correctly.

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

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

Schema description coverage is 0%, and description does not explain any parameters (mailbox, uid, targetMailbox). Agent must guess meaning from parameter names 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 states the verb 'move' and resource 'message' clearly. However, it does not differentiate from sibling tools like archive_message, which also involves moving messages.

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

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

No guidance on when to use this tool versus alternatives. Lacks context about prerequisites, when not to use, or exclusions.

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

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

Discloses automatic threading headers and requirement for user approval. However, with no annotations, could detail more about mutation and permissions.

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

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

Three short sentences, front-loaded with action, no redundancy.

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

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

With 6 parameters and no output schema or error handling described, the description is too minimal for an agent to fully understand invocation and results.

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

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

Schema description coverage is 0% and description adds no meaning for mailbox, uid, text, html, attachments. Only mentions replyAll briefly.

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

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

Description clearly states it replies to an existing message, distinguishing from siblings like forward and send_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?

Explicitly instructs to call only after explicit user approval, and mentions replyAll for reply-all. Does not specify when not to use or alternatives beyond the sibling 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?

No annotations provided. Description notes the non-sending behavior, but omits other behavioral traits like attachment handling, draft storage location, or server-side persistence.

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, directly informative. Ideal length for a tool with clear purpose.

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

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

No output schema, no description of return value or error conditions. For a complex tool with 9 parameters, the description is insufficient for an agent to use it confidently without additional context.

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 low (44%) and description adds no additional information beyond the schema. For example, the 'subject' parameter is required but undocumented, and 'cc'/'bcc' lack descriptions. The description should compensate for this gap.

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 saves a draft and notably clarifies it does not send the email, distinguishing it from sibling tools like send_email and compose_preview.

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 'Does not send', implying use when the user wants to review later. However, it does not provide guidance on when to use alternatives like compose_preview, forward, or reply.

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 states it returns summaries sorted newest first, which is helpful but omits any disclosure of authentication needs, rate limits, or safety guarantees. The tool is read-only, but the description does not explicitly confirm non-destructiveness.

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 at three short sentences, with no filler or redundant information. Every sentence adds value: function, filtering behavior, and output ordering. It is well-structured and easy to parse 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 has 9 parameters and no output schema or annotations, the description covers the core functionality and filtering behavior. However, it lacks mention of default limits (e.g., limit defaults to 25) or read-only nature, leaving some gaps in completeness for an agent to fully understand expected behavior.

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

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

Schema description coverage is 100%, so the schema already documents all parameters. The description adds that filters are combined with AND, but this is a minor addition. No extra semantic detail is provided beyond the schema's parameter 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 searches a mailbox, which is a specific verb-resource combination. It distinguishes from siblings like get_message or list_mailboxes by focusing on search with filters, and no other sibling tool has search in its name.

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 mentions that all filters are optional and combined with AND, which provides basic usage context. However, it does not explicitly state when to use this tool over alternatives (e.g., get_message for single messages, list_mailboxes for mailbox listing), nor does it provide exclusions or prerequisites.

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

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

No annotations are provided, so the description must cover behavioral traits. It only says 'Send an email NOW' implying immediate action, but does not disclose potential side effects (e.g., irreversibility), authentication requirements, rate limits, or what happens on success/failure. More transparency is needed for a tool that performs a real-world action.

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

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

Two sentences, front-loaded with the action and a clear usage condition. No filler or redundancy. However, it could include more useful details without becoming overly verbose.

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

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

Given the tool's complexity (9 parameters, no output schema, no annotations), the description is insufficient. It lacks details on return values, constraints (e.g., attachment limits), error handling, or post-send behavior. The context signals indicate high complexity, but the description does not address it.

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 44%. The description adds no parameter-level information beyond the schema, which already describes some parameters (to, text, html, attachments' path and contentBase64, inReplyTo). Undocumented parameters like cc, bcc, subject, and attachment properties remain unclear. The description should compensate for schema gaps but does not.

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 'Send an email NOW,' which is a clear verb+resource. It distinguishes from sibling tools like compose_preview, save_draft, reply, and forward that deal with email composition or other 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 provides explicit guidance: 'Only call after the user has explicitly approved sending (ideally after a compose_preview).' This tells when to use and suggests a prerequisite (compose_preview). However, it does not mention when not to use or alternative tools for other email actions.

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. It does not mention side effects (e.g., whether the operation is reversible), authentication needs, rate limits, or any constraints. This is an insufficient disclosure 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 a single, succinct sentence that conveys the core function without any extraneous words. It is well-structured and immediately understandable.

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 lack of an output schema, annotations, and only partial parameter descriptions, the description is too sparse. It does not explain return values, error handling, prerequisites, or the effect of not supplying optional parameters. A mutation tool like this requires more context for safe and correct invocation.

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

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

Schema description coverage is 50% (the boolean parameters seen and flagged have descriptions, but mailbox and uid do not). The description repeats the boolean usage without adding new information. It does not explain the mailbox and uid parameters, failing to compensate for the schema 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: marking a message read/unread and/or flagged/unflagged. It uses specific verbs (mark) and resources (message) and effectively distinguishes from sibling tools like archive_message or delete_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 for toggling read/flag status but does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives like using archive_message for moving messages. It is minimally adequate.

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