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

With no annotations, the description must fully disclose behavior. It mentions moving to Trash (not permanent delete), but omits potential side effects like whether the folder is cleared recursively, permission requirements, or rate limits. This is minimal for a powerful delete 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 sentence (11 words) that conveys the core action. It is front-loaded and avoids filler. However, it could be slightly more informative 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?

Despite an output schema, the description lacks crucial context for a destructive tool: no mention of irreversibility (even Trash can be emptied), impact on subfolders, or relationship to sibling tools. Annotations are absent, so the description should compensate but does not.

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% and includes examples and a suggestion to use list_folders. The description adds no additional semantics beyond what the schema already provides, so the baseline of 3 is appropriate.

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

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

The description clearly states the verb ('Delete all emails') and the resource ('in a folder'), with the specific action of moving to Trash, which distinguishes it from sibling tools like delete_email (single) and move_all_emails (move to arbitrary folder).

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?

While the purpose is clear, no guidance is given on when to use this tool versus alternatives like move_all_emails or delete_email. The usage context is implied 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?

The description only states the action (move to Trash) without disclosing behavioral traits such as whether the operation is reversible, requires permissions, or affects attachments. Since no annotations are provided, the description carries full burden but provides minimal disclosure.

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 with 12 words, front-loaded with the action. Every word is necessary and clear. 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?

For a simple tool with two parameters and an output schema, the description is adequate but lacks behavioral context (e.g., irreversibility). It does not leverage the output schema to explain return values.

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?

Input schema has 100% coverage, so baseline is 3. The description adds no new information beyond schema: it restates 'by its IMAP message ID' and does not clarify parameter formats or constraints.

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+resource pair ('Move an email to the Trash folder') and specifies the method (IMAP message ID). It clearly distinguishes from sibling tools like 'delete_all_in_folder' which handles bulk deletion.

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 (when you have an IMAP message ID) but does not provide explicit guidance on when not to use or mention alternatives like 'delete_all_in_folder' or 'move_email'.

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 says 'list all attachments', implying a read operation but does not mention potential errors, authentication needs, or side effects.

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 12-word sentence that is front-loaded and concise, containing no unnecessary 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?

The tool has an output schema (not shown but present), so return values need not be described. The description adequately covers the tool's purpose for a simple two-parameter tool, though it could mention that attachments are returned as a list.

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

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

The input schema has 100% coverage with clear descriptions for both parameters (message_id and folder). The tool description adds no additional semantics beyond the schema, meeting the baseline.

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 'List' and resource 'attachments in an email' with the identifier 'IMAP message ID', clearly distinguishing from siblings like read_email or 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 states what it does but gives no guidance on when to use versus alternatives like read_email or search_emails, leaving the agent to infer based on sibling names.

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 bullet list of folder names, which is a safe read operation. The simplicity of the tool makes this sufficient, though it could mention authentication or folder hierarchy.

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 short sentences, front-loading the purpose and then stating the return format. No unnecessary words, making it highly efficient.

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

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

Given there are no parameters and an output schema exists (though unseen), the description is largely complete for a simple listing tool. It could mention prerequisites or limitations, but for its scope, it suffices.

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, so baseline is 4 per scoring rules. The description adds meaningful context by specifying 'IMAP folders' and 'AOL mailbox', which goes beyond the empty schema.

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

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

The description clearly states 'List all IMAP folders', which is a specific verb+resource. It distinguishes itself from sibling tools that focus on email operations like delete, move, read, send, etc.

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 any guidance on when to use this tool over alternatives or any prerequisites. It simply states what the tool does without contextual usage advice.

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

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

No annotations are provided, so the description must carry the full burden. It only states the core function without disclosing side effects, idempotency, permissions, or whether the action is reversible. Very minimal behavioral disclosure.

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 7-word sentence, making it very concise. However, it is almost too terse; a bit more context (e.g., 'sets the seen flag') would not hurt efficiency.

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 low complexity of marking emails as read and complete schema coverage, the description is adequate but minimal. It could mention that the tool is idempotent or that it works on the specified folder, but is not severely lacking.

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%, and the description adds no extra meaning beyond what the schema provides. Baseline 3 is appropriate; the description does not elaborate on the comma-separated format or default folder.

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 ('mark') and resource ('one or more emails') with the result ('as read'). It distinguishes from sibling tools like delete_email or move_email by specifying a read-only state change.

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 (when you need to mark emails as read) but provides no explicit guidance on when not to use or alternatives. Siblings like read_email likely fetch content, but no differentiation 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 are provided, so the description carries full burden for disclosing behavioral traits. It states 'Move all emails' but does not disclose potential side effects (e.g., mass modification, performance impact, or irreversibility). The output schema exists but is not leveraged to explain return behavior.

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

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

The description is a single short sentence that is concise and front-loaded. However, it is too brief to cover all necessary aspects, so it does not earn a top score in this dimension.

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 that there are no annotations and the tool performs a bulk operation, the description is complete enough for basic understanding but lacks details on constraints (e.g., number of emails processed, reversibility). The output schema partially compensates for missing return 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?

Schema coverage is 100% and the schema already describes both parameters with examples and hints (e.g., 'use list_folders'). The description adds no additional meaning beyond the schema, so 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?

The description clearly states the action: 'Move all emails from one folder to another.' It uses a specific verb 'move' targeting the resource 'all emails' with clear source and destination scope. This distinguishes it from the sibling tool 'move_email' which operates on a single 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?

No guidance is provided on when to use this tool versus alternatives like 'move_email' for individual moves. There is no mention of prerequisites, limitations, or when not to use it. The description lacks usage context.

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

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

No annotations are provided, so the description must carry the full burden. It only states 'Move' without explaining permissions, reversibility, or behavior on errors (e.g., missing source folder). Minimal behavioral insight is given.

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 that is clear and to the point, with no wasted words. It effectively communicates the tool's action.

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?

Despite having an output schema (from context signals), the description is overly brief for a mutation tool with no annotations. It lacks context on side effects, prerequisites, or typical use cases, making it incomplete.

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

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

All three parameters have descriptions in the input schema (100% coverage), so the baseline is 3. The tool description adds no additional parameter context beyond what the schema already provides.

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 ('Move') and resource ('email') with a clear destination ('any named IMAP folder'), distinguishing it from sibling tools like 'move_all_emails' that move multiple 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?

No guidance is provided on when to use this tool versus alternatives, such as whether prerequisites like knowing the destination folder name via 'list_folders' are needed. The parameter description for 'folder' hints at this, but the main description lacks explicit context.

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

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

No annotations provided, so the description carries full burden. It implies a read-only operation but does not mention any behavioral traits such as authentication requirements, rate limits, or the nature of the returned data. The existence of an output schema partially mitigates this, but the description should hint at the response 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?

Single sentence with no unnecessary words. Front-loaded with the core 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?

For a simple read tool with output schema, the description is adequate but lacks behavioral context. It does not explain prerequisites (e.g., having a valid message ID) or any constraints.

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 both parameters well-documented. The description adds minimal value beyond the schema (e.g., stating the source of message_id). Baseline score of 3 is appropriate.

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

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

The description clearly states 'Get the full content of a single email by its IMAP message ID,' identifying the action, resource, and method. It distinguishes from sibling tools like read_inbox and get_attachments.

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. With 13 sibling tools, the description should mention when read_email is appropriate (e.g., after obtaining a message ID) and when other tools like read_folder or search_emails might be better.

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 bears full responsibility for behavioral disclosure. However, it only states 'List recent emails' without revealing side effects (e.g., whether it marks as read, fetches full content or headers, or is destructive). This leaves significant gaps for the agent.

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

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

The description is a single, concise sentence with no unnecessary words or redundancy. It efficiently communicates 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 an output schema exists and the tool is simple, the description is adequate but incomplete. It does not mention ordering or recency criteria, nor how it differs from similar tools like 'read_email' or 'read_inbox' (beyond the folder parameter).

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 100% schema description coverage, the schema already explains both parameters. The description adds no additional meaning beyond restating the action. Baseline score of 3 is appropriate.

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

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

The description clearly states the action ('List recent emails') and the specific resource ('from a named IMAP folder'). It distinguishes from siblings like 'list_folders' (which lists folder names) and 'read_inbox' (which reads the inbox specifically), making the purpose 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 does not explicitly state when to use vs. alternatives, but the parameter schema hints at a prerequisite: 'Use list_folders to see all available names.' This provides context for usage, though it lacks exclusions or 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?

No annotations are provided, so the description carries full burden. It only states basic function without disclosing whether emails are marked as read, authentication requirements, or any side effects. The output schema exists but is not referenced.

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 fluff, front-loaded. However, it is overly brief and could include more detail without sacrificing 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?

Given the complexity of sibling tools and presence of output schema, the description is too minimal. It lacks explanation of 'recent', whether the operation is read-only, and how results relate to other email tools.

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?

Input schema coverage is 100% with default values and descriptions for both parameters. The tool description adds no extra meaning beyond the schema, so 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 'List', resource 'recent emails', and scope 'any IMAP folder'. It effectively distinguishes from sibling tools like 'read_email' (single email) and 'search_emails' (search) by specifying batch listing across folders.

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 guidance on when to use this tool versus alternatives. With 12 sibling tools including 'read_email', 'search_emails', and 'read_folder', the description fails to provide context for selecting this tool over others.

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

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

With no annotations, the description should disclose behavioral traits. It only states the basic operation without mentioning whether the reply includes quoting, threading, attachments, or any side effects (e.g., sent folder).

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 very short but not overly concise; it contains only one sentence without front-loading critical info like required params or success conditions. Could be restructured to add 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 no annotations and an output schema exists, the description is incomplete. It lacks details about reply behavior (e.g., threading, auto-include subject), error handling, or confirmation of sending. Users would need to infer from the 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%, so parameters are already well-documented in the schema. The description adds only 'by its IMAP message ID', which is already present in the schema's description for message_id. 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?

The description clearly states the action ('Reply') and the resource ('existing email') using the IMAP message ID, which distinguishes it from siblings like send_email (new email) and delete_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?

No explicit guidance on when to use this tool versus alternatives like send_email or forward, but the purpose is implied by the 'Reply' verb. No exclusions or context are provided.

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 does not disclose whether the operation is read-only, what fields are returned, or any side effects. The behavioral context is insufficient for an AI agent to assess risks.

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 one short, front-loaded sentence with no unnecessary words. Every word serves a 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?

Despite having an output schema and full parameter coverage, the description lacks important details such as search query syntax, case sensitivity, or whether attachments are included. It feels incomplete for a tool with 4 parameters.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the schema's parameter descriptions, which are already clear.

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 ('Search'), the resource ('any IMAP folder'), and the criterion ('matching a keyword'). It effectively distinguishes from sibling tools like read_email and list_folders.

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 searching emails but provides no explicit guidance on when to use this tool vs alternatives, nor any 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 carries the full burden. It only states 'compose and send', but omits critical behavioral details such as whether sending is immediate, what error scenarios exist, or any rate limits. This is insufficient for a mutation tool.

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

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

The description is a single concise sentence with no fluff. However, it may be too brief, missing opportunities to add critical context without becoming 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 complexity of an email-sending operation (6 parameters, output schema present), the description is minimal. It does not explain authentication, sending behavior, or return value meaning. The presence of an output schema mitigates some need for return value explanation, but the lack of behavioral context is a 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 coverage is 100%, so the schema already documents all parameters fully. The description adds no additional meaning beyond what the schema provides, so 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?

Clearly states the verb 'compose and send' and the resource 'a new email via AOL SMTP'. It naturally distinguishes from siblings like reply_email and move_email by specifying 'new 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?

No explicit guidance on when to use this tool vs. siblings or prerequisites. The description relies on the tool name and sibling context, but fails to mention required authentication, SMTP configuration, or common alternatives.

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