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

The description discloses operational behavior: it processes up to max_results (default 20, max 100), can both add and remove labels, and returns a count and message IDs. Annotations already indicate mutation (readOnlyHint=false) and non-destructiveness (destructiveHint=false), so the description adds context about scope and return values without contradicting the annotations.

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 a clear one-sentence summary, followed by a well-organized Args list, query examples, return information, and usage scenarios. Each section is concise and relevant, with no redundant or unnecessary 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?

The description covers all parameters, provides usage examples, states the return value ('Count of messages updated and their IDs'), and clarifies the maximum scope. Since there is no output schema, the explicit return description is essential and provided. The tool's non-trivial behavior is thoroughly documented.

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?

Although the schema covers 100% of parameters, the description significantly enriches understanding by providing query examples (e.g., 'from:sender@example.com', 'subject:invoice', 'is:unread', date ranges) and clarifying the purpose of add_label_ids and remove_label_ids. It also explains the default and maximum for max_results, going beyond the schema 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 verb ('Search' and 'apply label changes') and the resource ('Gmail messages'). It distinguishes itself from sibling tools by emphasizing bulk operation via a search query rather than targeting specific message or thread IDs, as seen in gmail_modify_message_labels and gmail_modify_thread_labels.

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 usage examples ('Use when: "Label all emails from compliance@firm.com as Compliance"') and query syntax examples. It implies the tool is for bulk, search-based label changes, but it does not explicitly mention alternatives for single-message label changes, leaving the exclusion implicit rather than 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?

Annotations already indicate a non-read-only, non-idempotent operation. The description adds the return value (ID, name, visibility settings) and nesting behavior, but does not disclose potential duplicate handling or error cases. This adds some context but is not extensive.

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 compact and well-structured with distinct sections for Args, Returns, and Examples. Every line serves a purpose and there is no redundant 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?

For a simple one-parameter creation tool, the description is sufficiently complete: it explains what it does, when to use it, the return value, and includes examples. No significant gaps are apparent.

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 single 'name' parameter with the same nesting description (100% coverage). The description's Args section repeats this information without adding new semantics such as uniqueness constraints or format 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 uses the specific verb 'Create' and identifies the resource as 'a new user label (tag) in Gmail'. This clearly distinguishes it from sibling tools like gmail_list_labels and gmail_delete_label. Examples reinforce the 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 provides two 'Use when' examples that clearly indicate when to invoke this tool. However, it does not explicitly mention alternatives or exclusions, relying on sibling tool names for that 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?

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description adds valuable behavioral context: deleting a label removes it from all messages but does not delete the messages. This is important side-effect information not covered by the annotations.

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 compact and well-structured: it leads with the purpose, then explains the parameter, notes a critical caveat, and provides two clear usage examples. Every sentence adds value with 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 single-parameter mutation tool, the description is complete. It covers what the tool does, how to get the parameter, key behavioral caveats, and example usage. The annotations and full schema coverage fill in the remaining safety details.

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

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

The input schema already fully describes the single parameter ('label_id') with 100% coverage. The description adds extra value by instructing users to use gmail_list_labels to find IDs, which is helpful usage guidance beyond the 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 the tool deletes a user-created label from Gmail, using a specific verb+resource. It distinguishes itself from siblings by explicitly saying system labels cannot be deleted and by focusing on deletion rather than listing, creating, or modifying labels.

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 usage context: it explains when to use the tool with two practical examples. It also notes a key constraint (system labels cannot be deleted) which helps decide when not to use it, though it doesn't explicitly mention alternative tools for non-deletion operations.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, establishing the safety profile. The description adds return details (subject, snippet, label IDs) and example queries, providing extra behavioral context without contradicting annotations.

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 compact and well-structured: purpose, args, returns, and examples in a few lines. Every sentence adds value, with no redundancy or filler.

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 single-parameter read-only retrieval tool, the description is complete. Annotations cover safety, schema covers the parameter, and the description provides return type and use cases. No output schema exists, but the return description compensates sufficiently.

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 parameter message_id is self-explanatory. The description repeats the parameter but does not add new semantic meaning, so the baseline score of 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 'Retrieve' with a clear resource 'labels on a specific Gmail message.' The examples further clarify the scope, distinguishing this from sibling tools like gmail_list_labels (all labels) and gmail_modify_message_labels (changing labels).

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?

Two concrete 'Use when' examples provide clear scenarios for invocation. However, it lacks explicit 'when not to use' guidance or alternative tool mentions, such as when to use gmail_list_labels for global label listing.

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?

Annotations already declare the operation read-only, idempotent, and non-destructive. The description adds that both system and user-created labels are returned, along with their IDs, names, types, and message counts, giving a clearer picture of the response without contradicting annotations.

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?

Four sections—purpose, scope, return details, and two concrete usage examples—are packed into a compact description with no filler. Every line adds 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?

For a zero-parameter read-only tool, the description fully specifies its output, clarifies its use cases, and implies the broader label-management workflow via sibling tools. No output schema exists, but the return list is described in sufficient detail.

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 accepts zero parameters, so the schema fully covers all inputs. The description mentions the return fields (IDs, names, etc.), which is useful context but not required for parameter understanding.

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

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

The description opens with 'List all labels (tags) in the Gmail account', clearly identifying the action and resource. It distinguishes itself from sibling write tools by noting its role in finding label IDs for 'add/remove 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?

Provides explicit 'Use when' examples for common queries and mentions 'Use this to find label IDs needed for add/remove operations', indicating when it should be chosen over mutation tools. Sibling tools for creating/deleting/modifying labels make the context unambiguous, though no direct 'when not to use' statement is included.

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 discloses the return behavior ('Updated message with its current label IDs') and notes that removing the INBOX label archives the message. Annotations already indicate this is a mutating operation (readOnlyHint: false), so the added context is useful and does not contradict any annotation.

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 well-structured with Args, Returns, and Examples sections, making it easy to scan. However, the Args section partially duplicates the schema, adding some redundancy. Overall, it is focused and every sentence carries useful 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?

The description is complete for a tool of this complexity: it covers purpose, parameters, return value, and common use cases. With no output schema or explicit prerequisites, the description still gives enough detail for an agent 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?

Despite 100% schema description coverage, the description adds significant value by providing common system label IDs (INBOX, STARRED, etc.) and concrete examples for each parameter (e.g., 'Star message abc123' -> add_label_ids: ['STARRED']). This goes beyond the schema's basic 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 'Add or remove labels (tags) on a specific Gmail message', which is a specific verb+resource+scope. It distinguishes from sibling tools like gmail_modify_thread_labels (modifies a thread) and gmail_bulk_label_by_search (bulk operation) by emphasizing 'specific Gmail 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 provides concrete usage context with 'Use gmail_list_labels to find label IDs' and multiple 'Use when' examples. It does not explicitly exclude alternatives like thread-level or bulk operations, but the examples make it clear this is for single-message label modifications.

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 discloses the scope ('all messages in a Gmail thread at once'), the return format ('Updated thread with message count and affected message IDs'), and implies a mutation operation. Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, and the description adds context without contradicting them. It does not cover edge cases, but overall adds useful behavioral detail.

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

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

The description is concise and well-structured with sections for the summary, Args, Returns, and Examples. It is front-loaded with the core purpose and avoids unnecessary verbiage. 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?

For a 3-parameter mutation tool with annotations and no output schema, the description covers purpose, parameters, return value, and usage examples. It is complete enough for an agent to select and invoke the tool correctly. The lack of edge-case details is acceptable given the simplicity and the provided structured data.

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

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

Schema coverage is 100%, and the description repeats the parameter meanings. The added example for remove_label_ids ('Archive this thread') gives practical semantics beyond the schema's bare definitions, making the tool more intuitive. Baseline is 3, and the example raises it to 4.

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: 'Add or remove labels on all messages in a Gmail thread at once.' The verb 'Add or remove' and specific resource 'labels on all messages in a Gmail thread' is explicit. The title and description distinguish this from sibling tools like gmail_modify_message_labels by emphasizing the thread-level scope.

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 concrete 'Use when' examples, such as 'Label this entire conversation as Compliance' and 'Archive this thread' with remove_label_ids: ['INBOX']. This offers clear context for when to use the tool, but it does not explicitly mention alternatives or state 'when not to use', leaving a slight gap.

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