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 key behavioral distinction (list vs. download) and the side effect of writing to a directory when output_dir is set. It does not detail error handling or return formats, but the core behavior is clear.

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

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

The description is two sentences, with the primary action in the first sentence and the conditional in the second. Every word contributes to understanding the tool's behavior, with no fluff 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?

For a two-parameter tool with no output schema, the description covers the main usage scenarios. However, it lacks information about return values, error conditions, or what happens when there are no attachments, which would be useful given the absence of an output schema.

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

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

Schema coverage is 100% for both parameters, so the baseline is 3. The description essentially restates the conditional logic already present in the schema ('omit to just list attachments') and adds no additional parameter meaning beyond that.

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 verbs 'List' and 'download' with the clear resource 'attachments from an email'. It explicitly distinguishes itself from sibling email tools by focusing on attachments and explains the conditional behavior based on output_dir.

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 clearly states when to use each mode: omit output_dir to list, set it to download. This provides context for correct invocation, though it does not explicitly mention alternatives 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?

No annotations are provided, so the description carries the burden. It states output and ordering but does not explicitly confirm read-only nature or absence of side effects. The verb 'list' implies a read operation, but for full transparency an explicit statement would be better.

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

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

Two concise sentences that front-load the action and scope, followed by output details. No wasted words.

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

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

Given the simple tool with one optional parameter and no output schema, the description provides enough detail including output fields. It could mention the meaning of 'recent', but the count parameter covers listing volume. Complete for the tool's complexity.

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

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

Schema coverage is 100% for the single 'count' parameter. The description adds no further detail about the parameter, so the baseline of 3 applies since the schema already documents it 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 tool lists recent emails with all statuses, newest first, and specifies output fields. This distinguishes it from sibling tools like list_unread_emails by explicitly including 'all statuses'.

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 when to use this tool (when you need all emails regardless of status) by contrasting with unread-only alternatives. It does not explicitly name alternatives but gives clear context that this is the broad-list option.

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 result order (newest first), the returned fields, and the attachment indicator, which adds meaningful behavioral context. However, it does not mention potential side effects (e.g., whether reading changes read state) or error/empty behavior, leaving some room for improvement.

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

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

The description is two concise sentences, front-loaded with the core purpose. Every clause adds value: the output fields and attachment indicator are essential information. 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 list tool with one optional parameter and no output schema, the description is complete: it specifies purpose, ordering, output structure, and attachment behavior. Combining the description with the schema gives an agent everything needed to invoke the tool correctly.

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

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

The schema already fully describes the count parameter (100% coverage) with default value, so the description adds no additional parameter-level semantics. Per the rubric, baseline 3 is appropriate when schema covers all 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 tool's function with a specific verb and resource: 'List unread emails'. It also provides key output details (ID, From, Subject, Received) and ordering (newest first), which distinguishes it from sibling tools like list_emails (all emails) and search_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 implies the tool is for retrieving unread emails but does not explicitly say when to use it versus alternatives, nor does it mention exclusions or alternative tools. There is no guidance such as 'Use search_emails for filtering' or 'Use list_emails for all 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?

No annotations are provided, so the description carries the full burden. It states the mutation (mark read) but does not disclose return values, side effects, permissions, or whether the operation is idempotent. This is a significant gap for a state-changing 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?

One concise sentence of 11 words, front-loaded with the action and resource. No filler 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?

The tool is simple and the description covers the core action, but with no output schema it fails to disclose what the agent can expect after invocation (e.g., success/failure, return value). This is a clear but non-fatal 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?

The single parameter 'id' is fully documented in the schema (100% coverage), including where to obtain it. The description adds no information beyond the schema, warranting the baseline score of 3.

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

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

The description uses a specific verb ('Mark'), a specific resource ('an email'), and the input method ('by message ID'). This clearly distinguishes it from sibling tools like send_email, reply, or read_email, which have different 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 does not explicitly state when to use this tool versus alternatives. The schema parameter description adds a helpful hint ('get from list_emails or list_unread_emails'), but there is no guidance on exclusions or comparisons to read_email or 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?

No annotations are present, so the description must carry the behavioral disclosure burden. It does disclose what the tool returns (From, To, CC, Subject, Date, Body, Attachments), which is useful. However, it does not mention whether reading an email has side effects (e.g., marking it as read), error behavior, or authentication requirements. The description is functional but not rich in behavioral context beyond the output structure.

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 followed by a concise list of returned fields. It is front-loaded with the core action and resource, and every word earns its place. No filler 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 tool's simplicity (one parameter, no output schema), the description adequately explains what the tool returns and how to get the required ID. It lacks an explicit statement about side effects or errors, but for a read operation with clear return fields, it is sufficiently complete. The presence of sibling tools like thread hints at potential richer alternatives, but this tool's scope is well-defined.

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

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

The input schema already covers the only parameter (id) with a description that includes provenance ('get from list_emails or list_unread_emails'). The tool description merely repeats 'by message ID' without adding new semantic details. Since schema coverage is 100%, the description adds minimal value beyond the structured schema.

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

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

The description uses the specific verb 'Read' with the resource 'email content by message ID', clearly distinguishing it from siblings like list_emails (listing) and mark_read (changing state). It lists the exact fields returned, making the tool's purpose unmistakable.

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 context by stating 'by message ID' and the schema param description directs users to get the ID from list_emails or list_unread_emails. While it doesn't explicitly say 'use this instead of list_emails for full content', the workflow is clear enough. No exclusion or alternative guidance is given, but the context signals and param description provide adequate direction.

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

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

No annotations are provided, so the description must disclose behavioral traits. It only mentions the scope of the reply ('original sender only'), but omits critical aspects such as the side effect of sending an email, any permission requirements, behavior regarding attachments/HTML, or how the reply interacts with the email thread. This is insufficient for a mutation tool with zero 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, front-loaded sentence that states the action and scope without any filler or redundant information. It is appropriately concise for a simple 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?

The tool has no annotations, no output schema, and is a side-effecting operation. The description covers the core purpose but lacks context on when to choose this over 'send_email', whether the original message is quoted, or what the agent should expect as a response. It is adequate for basic understanding but incomplete for robust agent decision-making.

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

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

The input schema provides descriptions for 100% of the parameters, so the description does not need to add param-level details. The baseline score of 3 applies because the schema already documents 'id', 'body', 'html', and 'attachments' adequately, and the description adds no additional parameter semantics.

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 function: 'Reply to the sender of an email', with the parenthetical '(reply to original sender only)' further specifying scope. This distinguishes it from the sibling tool 'reply_all', which is present in the sibling list.

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

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

The description provides an explicit scope ('original sender only'), which implies when to use this tool versus 'reply_all'. However, it does not explicitly name alternatives or discuss when to use 'send_email' over 'reply'. The context is clear for the reply vs reply-all distinction but lacks broader usage 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?

No annotations are provided, so the description carries the full burden. It usefully specifies the recipient set (sender, To, CC), implicitly excluding BCC. However, it does not mention other behavioral aspects such as sending confirmation, error conditions, or whether the reply includes any default headers. This is adequate but not rich.

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

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

The description is a single, focused sentence that states the action and its scope without any filler or redundancy. It is perfectly concise and front-loaded.

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

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

For a relatively simple 4-parameter email action with no output schema, the description combined with the schema covers the core behavior and parameters adequately. It does not explain edge cases or response format, but those are not critical for this tool's simplicity. The description is sufficiently complete for an agent to select and invoke 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 100%, so the schema already fully documents all four parameters (id, body, html, attachments). The description adds no additional parameter-specific semantics, which is acceptable given the schema's completeness. Baseline 3 applies.

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

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

The description uses a specific verb ('reply') and clearly identifies the resource ('an email') and the scope ('original sender, To, and CC recipients'), which distinguishes it from the sibling tool 'reply' that likely targets only the sender. This is a clear, unambiguous purpose.

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 clearly implies when to use this tool: when the user wants to reply to all original recipients. However, it does not explicitly state when not to use it or directly contrast it with the sibling 'reply' tool, so it falls short of full explicit 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?

With no annotations, the description carries the full burden for behavioral disclosure. It does not mention that the search is read-only, what the return format is, or any limitations (e.g., default folder, count). The description is minimal and adds no behavioral context beyond what's already implied by the tool name.

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 exceptionally concise: two short sentences that front-load the core purpose and quickly specify a usage pattern. No redundant or filler content.

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

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

Given the tool has 6 optional parameters and no output schema or annotations, the description is adequate but leaves gaps. It does not describe the shape of results (e.g., full emails vs. headers) or mention default values, though these are partially in the schema. It covers the main usage but lacks richness.

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

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

The schema covers all parameters at 100%, so the baseline is 3. The description adds semantics by explaining the query parameter as an alternative to combining from/subject/since filters, which is useful strategic guidance beyond individual 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's purpose with a specific verb ('Search') and resource ('emails'). It distinguishes the tool from siblings like list_emails and read_email by emphasizing search by various criteria, which is a distinct operation.

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 parameter usage guidance ('Use query for full-text search or combine from/subject/since filters'), but does not explicitly contrast when to use this tool versus list_emails or list_unread_emails. It gives clear context without exclusions, so a 4 is appropriate.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'Send an email via MS365 mailbox' and does not mention side effects, required permissions, rate limits, or what happens on success/failure. This is a significant gap 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 sentence, front-loaded with the action, and contains no redundancy or unnecessary detail.

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 6 parameters (3 required), no annotations, and no output schema, the description is too sparse. It fails to provide usage context, differentiate from sibling tools, or describe behavioral implications, making it incomplete for an agent to select and invoke correctly.

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

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

Schema description coverage is 100%, so the schema already documents all six parameters. The description adds no additional parameter semantics, leaving the baseline at 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 'Send an email via MS365 mailbox' clearly states the verb (send) and resource (email), and implies a new message rather than a reply. However, it does not explicitly differentiate from sibling tools like reply or reply_all, so it's clear but lacks explicit sibling distinction.

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 such as reply, reply_all, or search_emails. It only states the action without any context, 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that all messages in the conversation are fetched and sorted oldest first, but it omits potential side effects (e.g., whether it marks emails as read) or limitations (e.g., handling of deleted messages). This is 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 two concise sentences that state the purpose and key behavioral detail (sorting) without any wasted words. It is front-loaded 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 simple tool with one parameter and no output schema, the description covers the essential purpose and behavior. It could potentially hint at the return format, but that is implicit in 'Show full conversation thread'. Overall, it is sufficiently 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 provides a full description of the 'id' parameter ('Message ID of any email in the thread'), so the description doesn't need to add additional parameter details. The baseline of 3 applies because schema coverage is 100%.

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

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

The description uses a specific verb ('Show') and resource ('full conversation thread for an email'), clearly distinguishing it from sibling tools like read_email which likely reads a single message. It also mentions the sorting behavior (oldest first), adding 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 makes clear when to use this tool: to see the full conversation thread rather than a single email. However, it does not explicitly state when not to use it or name alternatives, so it falls short of a 5.

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