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

No annotations are provided, so the description must carry the burden. It implies a read-only operation ('list'), but does not disclose any potential behavioral traits (e.g., no mention of caching, authentication, or output limitations). Given the simplicity, a 3 is adequate.

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 with 6 words, front-loading the essential information. Every word is necessary and no waste.

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 no parameters, no output schema, and a simple read purpose, the description is complete. It specifies what is returned (alias -> email mapping).

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?

There are zero parameters, and schema coverage is 100% (empty schema). The description adds no extra parameter meaning, which is acceptable as there is nothing to document. The baseline for 0 params is 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 'List connected Google accounts (alias -> email)' using a specific verb and resource, and the tool name 'accounts_list' matches this purpose. It distinguishes itself from sibling tools which are all calendar and Gmail related.

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 use cases or alternatives are given, but the context of sibling tools (calendars, gmail) makes it obvious that this tool is for account listing. A slightly higher score would require explicit when-not guidance, which is unnecessary here.

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

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

Discloses invitation behavior (Google sends real invites). No annotations exist, so description carries burden. Missing details on other behaviors (e.g., date format, defaults).

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 front-loaded action. Concise but could be slightly more structured. 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?

Lacks detail on required parameters (datetime format, account selection), no output schema info. Incomplete for a 9-parameter tool with no annotations.

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 0% schema description coverage, description only clarifies 'attendees' and 'send_invites' via 'optionally inviting'. No explanation for 7 other parameters (account, start, etc.).

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?

Clear verb 'Create' and resource 'event'. Distinguishes from sibling tools like calendar_events (read) and calendar_list (list calendars) by being the only creation tool.

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

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

Explicitly warns about real invitations, advising user confirmation. Provides context-sensitive guidance, though lacks explicit alternative conditions.

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

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

No annotations provided; description lacks behavioral details such as pagination, rate limits, authorization, or handling of recurring events. Only mentions ISO date format. Inadequate for a listing tool without annotation safety net.

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 efficiently conveys core purpose and key details. 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 output schema exists, description covers main behavior: date range, account scope, calendar default. Could mention sorting, limits, or filtering, but not essential for basic use.

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 0%; description adds minimal meaning: only clarifies that calendar_id defaults to primary and that dates are ISO format. Other parameters (account, start, end) are not elaborated beyond their names and schema defaults.

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 'List events' with specifics: between two ISO dates/datetimes, across one or all accounts, and calendar_id defaults to primary. Distinguishes from siblings like calendar_create_event (create) and calendar_list (list calendars).

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?

Implies usage for listing events but provides no explicit guidance on when to use vs alternatives, nor when not to use. Sibling names suggest distinct purposes but no 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?

With no annotations, the description should disclose behavioral traits. It does not mention side effects, authentication, or output format. The presence of an output schema mitigates but does not replace description context.

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

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

The description is a single front-loaded sentence with no waste. However, it is under-specified, sacrificing completeness for brevity.

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 single-parameter schema and output schema, the description still lacks context on when to use this tool (e.g., to get calendar IDs for events), and does not explain the 'all' default behavior.

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

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

Description adds meaning by stating 'for one or all connected accounts', linking the 'account' parameter to accounts. However, it does not specify value format or how to specify a single account. Schema coverage is 0% so description is essential.

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 (list) and resource (calendars), and distinguishes from siblings like calendar_events and calendar_create_event. However, it lacks title and could clarify that these are calendar objects, not events.

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 vs alternatives like calendar_events or accounts_list. The agent is left to infer from 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 checks credentials, accounts, and API responsiveness, which is sufficient for a diagnostic tool. However, it does not describe output format or behavior on failure, leaving minor ambiguity.

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, clear sentence with no extraneous words. It effectively conveys the tool's function without waste.

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 no parameters, no output schema, and a simple diagnostic function, the description is fully complete. It covers what the tool checks without needing additional 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 has zero parameters, and schema coverage is 100%. The description adds no parameter information, but none is needed. Baseline for 0 params is 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 purpose: 'Diagnose setup: credentials file, connected accounts, and whether each account's Gmail API actually responds.' It uses a specific verb (diagnose) and resource (setup), and distinguishes itself from sibling tools that perform other actions like sending or reading 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 verifying setup before using other Gmail tools, but does not explicitly state when to use it vs. alternatives or include exclusions. The context makes it clear, but a more explicit guideline would improve it.

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 the key trait that the tool does not send, which is critical for safe usage. However, it omits other behavioral aspects such as authentication requirements, rate limits, or where drafts are stored, leaving gaps in transparency.

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

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

The description is extremely concise—two short clauses that front-load the main purpose ('Create a draft') and add a critical safety note. Every word contributes value, with 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 low complexity (5 parameters, no output schema), the description is too minimal. It does not explain return values, side effects beyond not sending, or any post-creation behavior. A more complete description would mention what happens after draft creation (e.g., draft ID returned, stored in drafts folder).

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

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

Schema description coverage is 0%, and the description provides no additional meaning beyond the input schema. It does not explain any parameter, such as the required 'account', 'to', 'subject', or 'body', nor the optional 'cc'. The description fails to compensate for the lack of schema documentation.

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 ('Create a draft') and explicitly distinguishes it from the sibling tool 'gmail_send' by noting it does not send. This combination of specific verb and resource with sibling differentiation earns a top score.

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 by labeling it as the 'Safer default than gmail_send,' implying its use when avoiding immediate sending. However, it lacks explicit exclusions or alternative tools beyond gmail_send, which prevents 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, the description must disclose behavioral traits but only states the action. It does not mention authentication needs, rate limits, or what happens if the account is invalid.

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 wasted words, front-loading 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?

The tool is simple with one parameter and an output schema, so the description suffices for basic understanding. However, it lacks context on error handling and parameter format, leaving gaps for complete invocation.

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

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

The schema has 0% description coverage; the only parameter 'account' is not explained in the description (e.g., format as email). The description adds no semantic value beyond the schema title.

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 'list' and the resource 'label names for one account', distinguishing it from sibling tools like gmail_read or gmail_search.

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 gmail_search or gmail_read. The description does not mention any context 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 fully bears the transparency burden. It discloses reversibility ('nothing is deleted') and automatic label creation, which are key behavioral traits. Missing details on rate limits, auth scopes, or error handling for exceeding 500 messages.

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

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

A single sentence that is front-loaded with the core action ('Batch-modify up to 500 messages') and efficiently lists operations. 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 6 parameters, no output schema, and no annotations, the description covers the main actions and reversibility. It lacks details on return values, error cases, and parameter constraints (e.g., message_ids format). Overall sufficient for common use.

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 0% schema description coverage, the description must compensate. It explains the effects of archive, mark_read, add_labels, remove_labels, but does not detail the format of message_ids or label strings. It adds some meaning beyond the schema's property titles but not comprehensively.

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 it batch-modifies messages with specific actions (add/remove labels, archive, mark read). It distinguishes from siblings like gmail_read (reading) and gmail_search (searching) by focusing on modification operations.

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

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

The description explicitly mentions 'batch-modify up to 500 messages' and lists the actions, implying use for bulk modifications. However, it does not provide explicit 'when to use vs when not' or compare to single-message 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?

No annotations are provided, so the description bears full burden. It claims to read the 'full body', but the input schema includes a max_chars parameter (default 20000) that truncates the content, contradicting 'full body'. This important behavioral trait is not disclosed.

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 waste, but it sacrifices clarity for brevity. It could include essential details like the max_chars limitation without being 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 no output schema, 0% parameter coverage, and no annotations, the description is incomplete. It fails to mention the truncation behavior, output format, or any prerequisites. A read tool with these features requires more information to be fully usable.

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

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

Schema description coverage is 0%, so the description must add meaning. It only mentions 'id' (message_id), ignoring account and the critical max_chars parameter (which limits the body). No explanation of how parameters affect behavior.

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 'read' and the resource 'one message's full body', and it references the source ('by the id from gmail_search'), which distinguishes it from sibling tools like gmail_search (list) and gmail_send (send). However, it could be more precise about what 'full body' includes (e.g., attachments, headers).

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 alternatives. It implicitly suggests use after gmail_search, but lacks when-not conditions or prerequisites. No mention of alternatives.

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 explains the account parameter and query syntax but fails to disclose key behaviors like pagination, rate limits, or that it returns a list of messages.

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

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

Two sentences with no wasted words. All key information is front-loaded: purpose first, then account details. Very concise.

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 a search tool and presence of output schema, the description adequately covers purpose and account handling but lacks details on pagination, default behavior, or scope of results. Minimal but functional completeness.

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

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

Schema coverage is 0%, so the description must compensate. It adds meaning for 'account' and gives query syntax examples, but does not define 'limit' or describe the 'query' parameter's expected format beyond examples. Partial addition of value.

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

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

The description clearly states the tool searches mail using Gmail's full query syntax, providing specific examples (from:, subject:, is:unread). It distinguishes from siblings like gmail_read (single email) and gmail_draft.

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 complex searches but does not explicitly state when to use this tool versus alternatives like gmail_read or gmail_modify. No when-not conditions or alternative references are 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?

With no annotations, the description adds the confirmation requirement but does not disclose other behavioral traits like permissions, rate limits, or side effects of sending. The confirmation directive is useful but insufficient for full transparency.

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

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

The description is concise with two sentences, but the second sentence is a guideline rather than structural content. It is front-loaded but sacrifices completeness for brevity.

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 5 parameters with 0% schema coverage and no output schema, the description is severely incomplete. It fails to explain required fields, account context, or body/cc/subject semantics.

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

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

Schema description coverage is 0%, and the description provides no additional meaning for any of the 5 parameters. The agent must rely solely on parameter names in the schema, which lack detail.

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 'Send' and the resource 'email from one account', but does not differentiate from sibling tools like gmail_draft or gmail_modify. It is adequate but not distinctive.

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

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

The description includes a confirmation directive but fails to specify when to use this tool versus alternatives such as gmail_draft or gmail_modify. No context on prerequisites or excluded use cases.

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