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 effectively describes the return format (email summaries with specific fields) and clarifies what is not included (email body), which is valuable context. However, it lacks details on potential behavioral traits like pagination, rate limits, authentication requirements, or error handling, leaving some 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, followed by essential details on return values and tool differentiation. Every sentence adds value—clarifying included fields, excluded content, and when to use alternatives—with no redundant or unnecessary information, making it highly 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 moderate complexity (listing emails with filtering), no annotations, and no output schema, the description does a good job by specifying the return format and tool differentiation. However, it could be more complete by mentioning potential limitations (e.g., pagination, default sorting) or error scenarios, which would help an agent use it more effectively in varied contexts.

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

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

The schema description coverage is 100%, so the schema already documents both parameters ('status' and 'mailbox_id') with descriptions and enum values. The description does not add any parameter-specific information beyond what the schema provides, such as default behaviors or usage examples. This meets the baseline of 3 for high schema coverage without additional param details.

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 emails in your inbox') and resource ('emails'), distinguishing it from siblings like 'read_email' (which gets full content) and 'list_mailboxes' (which lists mailboxes rather than emails). It provides precise scope by mentioning what's included (summaries with specific fields) and what's excluded (email body).

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

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

The description explicitly states when to use this tool ('List emails in your inbox') versus alternatives ('call read_email with the email ID to get the full message content'), providing clear guidance on tool selection. It differentiates from 'read_email' by specifying that this tool returns summaries only, not full content.

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 what the tool returns ('Returns each mailbox's ID, email address, oversight mode, and display name'), which is valuable behavioral information. However, it doesn't mention potential limitations like pagination, rate limits, or authentication requirements, leaving some 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 two sentences: the first states purpose and return values, the second provides usage guidance. Every word earns its place, and the structure is front-loaded with the core functionality.

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 annotations, no output schema), the description is quite complete. It explains what the tool does, what it returns, and when to use it. The only minor gap is the lack of output format details, but for a list operation this is acceptable.

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

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

The tool has 0 parameters with 100% schema description coverage, so the baseline would be 4. The description appropriately doesn't discuss parameters since there are none, which is correct and efficient.

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 mailboxes') and resource ('available to this API key'), distinguishing it from sibling tools like check_inbox or read_email which operate on specific mailboxes rather than listing them. It provides a concrete purpose beyond just the tool 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 explicitly states when to use this tool: 'Use this to discover your mailbox ID if MULTIMAIL_MAILBOX_ID is not set.' This provides clear guidance on the primary use case and distinguishes it from alternatives like check_inbox which require a mailbox ID.

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 effectively describes key behaviors: it retrieves email content and 'Automatically marks unread emails as read,' which is a critical side effect not obvious from the tool name. It lacks details on error handling or rate limits, but covers the main operational behavior.

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

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

The description is appropriately sized and front-loaded, with three concise sentences that each add value: the first states the purpose, the second reveals a key behavioral trait, and the third provides usage guidance. There is no wasted text.

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 (read operation with side effects), no annotations, and no output schema, the description is mostly complete. It covers purpose, behavior, and usage context, but lacks details on return values (e.g., structure of the response) and error conditions, which 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 documents both parameters ('email_id' and 'mailbox_id') fully. The description adds no additional parameter semantics beyond what the schema provides, such as format examples or usage tips, meeting the baseline for 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 ('Get the full content'), resource ('a specific email'), and scope ('including the markdown body and attachment metadata'). It distinguishes from siblings like 'check_inbox' (which lists emails) and 'send_email' (which sends emails).

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 ('Use the email ID from check_inbox results'), establishing a workflow dependency. However, it does not explicitly state when not to use it or name alternatives (e.g., vs. 'search_identity' for finding emails).

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 and does so well by disclosing key behavioral traits: automatic threading header handling, markdown body format, error responses (403 with upgrade instructions), and queuing behavior for gated oversight ('pending_approval' status). It does not cover all possible behaviors like rate limits or auth needs, but adds substantial context beyond basic functionality.

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, starting with the core purpose and then adding critical behavioral details. Every sentence adds value, such as error handling and status warnings, with 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 the complexity of an email reply tool with no annotations and no output schema, the description is mostly complete, covering purpose, usage context, and key behaviors. However, it lacks details on return values or success responses, which could be important for agent handling, preventing a perfect score.

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 does not add meaning beyond the schema, such as explaining parameter interactions or constraints. Baseline 3 is appropriate as the schema handles parameter documentation adequately.

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

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

The description clearly states the specific action ('Reply to an email in its existing thread') and resource ('email'), distinguishing it from siblings like 'send_email' (new email) and 'read_email' (viewing). It specifies that threading headers are handled automatically, which adds precision.

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 mentioning error conditions (403 error for read-only mode, 'pending_approval' for gated oversight) and advising against retries in specific cases. However, it does not explicitly compare to alternatives like 'send_email' or state when not to use it, keeping it from 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 effectively describes key behavioral traits: the rate limit ('Rate limited to 1 request per 5 minutes'), the precondition ('Only works for unconfirmed accounts'), and the specific use case (accounts stuck in pending_operator_confirmation). However, it doesn't mention error conditions or what happens after the email is resent.

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 three sentences that each serve a distinct purpose: stating the action, providing usage context, and disclosing behavioral constraints. There is zero wasted text, and the most critical information (what the tool does) is front-loaded.

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

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

Given the tool's moderate complexity (administrative action with rate limits), no annotations, and no output schema, the description does a good job covering the essential context: purpose, usage conditions, and behavioral constraints. However, it doesn't describe what the tool returns or what happens after the email is sent, leaving some gaps in 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 baseline would be 4. The description doesn't need to explain parameters, but it does implicitly confirm there are no required inputs by describing the tool's function without mentioning any parameters.

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 ('Resend the operator anti-spam confirmation email') and the resource it operates on (confirmation emails for accounts). It distinguishes this tool from siblings by focusing on a specific administrative function rather than general email operations like sending, reading, or searching.

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

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

The description explicitly states when to use this tool ('if the account is stuck in pending_operator_confirmation status because the original confirmation email was lost or filtered') and when not to use it ('Only works for unconfirmed accounts'). This provides clear context and exclusions, though it doesn't name specific alternative 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 full burden and does well by disclosing key behavioral traits: it's a read-only lookup ('look up'), requires no authentication ('No authentication required'), and describes the return content. However, it doesn't mention potential errors, rate limits, or data freshness, leaving some 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 efficiently structured in two sentences: the first states purpose and returns, the second provides usage guidance. Every phrase adds value with zero waste, making it easy to parse and front-loaded with 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?

For a simple lookup tool with 1 parameter and no output schema, the description is nearly complete: it covers purpose, usage, behavioral aspects, and return values. It lacks details on error cases or output structure, but given the low complexity, this is a minor gap.

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 the single 'address' parameter. The description adds no additional parameter details beyond implying it's for email addresses, which the schema's format already specifies. 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 verb ('look up') and resource ('public identity document for any MultiMail email address'), specifying it returns operator, oversight mode, capabilities, and verification status. It distinguishes from siblings like check_inbox or send_email by focusing on identity verification rather than email 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?

It explicitly states when to use this tool ('to verify another agent's identity before sending sensitive information'), providing clear context for its application. While it doesn't name specific alternatives, the guidance is direct and actionable for the intended use case.

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 excellently describes multiple behavioral traits: markdown-to-HTML conversion, error handling for read_only mode (403 with upgrade instructions), and gated oversight behavior (pending_approval status with no-retry policy). This provides comprehensive behavioral context beyond basic functionality.

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 with three sentences, each serving a distinct purpose: core functionality, error handling, and approval workflow. There's zero wasted language, and critical information is front-loaded about the main sending functionality before detailing edge cases.

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 provides exceptional completeness. It covers the core functionality, input format (markdown), error scenarios (403, pending_approval), and behavioral constraints (no retry). This gives the agent sufficient context to use the tool correctly despite the lack of structured metadata.

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

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

The schema description coverage is 100%, so the baseline is 3. The description doesn't add specific parameter semantics beyond what's in the schema, though it does mention markdown format for the body which aligns with the schema's 'markdown' parameter description. No additional parameter context is provided.

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 ('send an email'), identifies the resource ('from your MultiMail address'), and distinguishes it from siblings like 'reply_email' or 'check_inbox' by focusing on sending new emails. It provides additional context about markdown conversion that further clarifies its unique 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 explicitly provides when-to-use guidance by mentioning the 'read_only mode' scenario (returns 403 error) and directing users to 'use request-upgrade' as an alternative. It also explains the 'pending_approval' status for gated oversight mailboxes and explicitly states 'Do not retry or resend' in that case, providing clear usage boundaries.

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