Search Gmail and Outlook, save drafts, manage email rules, and view email stats.
Scored across 17 tools
Several tool pairs overlap confusingly: read_mail vs read_thread both read threads, create_draft vs save_mail_draft both create drafts, browse_mail vs search_inbox vs open_mail all touch browsing/searching mail, and get_response_time_stats vs get_stats_by_period both return stats. Descriptions attempt to differentiate (e.g. read_mail for 'mail interface', read_thread for inbox threads), but boundaries remain fuzzy enough to risk misselection.
Every tool follows a clean snake_case verb_noun pattern (browse_mail, change_mail, create_rule, list_rules, update_rule, send_mail, search_inbox, etc.). The convention is applied uniformly across mail, rule, and stats tools with no camelCase or stylistic drift.
17 tools is slightly heavy but reasonable given three sub-domains (mail operations, rule CRUD, analytics) plus account listing. Each tool maps to a distinct action, though a couple (the two draft creators, the two stats tools) could be consolidated.
Coverage is solid: mail read/browse/search/send/state-change with draft handling, full rule lifecycle (create, get, list, update, delete), and analytics, plus account listing. Minor gaps remain: no tool to link/create an email account (despite descriptions telling users to link one), and no delete/discard message operation.
List paginated mailbox threads and sidebar navigation. Browse a system view or a provider label/folder ID returned in navigation. Search uses the mailbox provider's syntax. Account ID comes from list_email_accounts.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| folder | Yes | System view: inbox, sent, draft, archive, starred, unread, all, spam, or trash; or a provider label/folder ID from the browse result's navigation. Use IDs only from the selected mailbox. | |
| pageToken | No | ||
| emailAccountId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds that results are paginated, that navigation/sidebar data is returned, and that folder IDs are mailbox-scoped, which is useful but modest extra behavioral 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?
Three short sentences, front-loaded with the core action, and each sentence adds a distinct fact (pagination, folder source, account source). No filler, though the middle sentence mixes usage and parameter notes slightly.
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 read-only browsing tool with no output schema, the description covers pagination, result composition (threads plus navigation), and required ID provenance. It omits detail on how pageToken is obtained, but annotations and schema cover enough that this is a minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 25%, so the description carries real weight: it explains that query uses the provider's search syntax and that emailAccountId should come from list_email_accounts, neither of which the schema documents. Folder meaning is largely already in the schema, so it stops short of a 5.
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 gives a specific verb and resource ("List paginated mailbox threads and sidebar navigation") and scopes it to browsing system views or provider folders, which separates it from read_mail/read_thread. It does not explicitly name the sibling search_inbox it overlaps with, so it falls short of a 5.
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?
"Browse a system view or a provider label/folder ID returned in navigation" gives implied usage context, and "Account ID comes from list_email_accounts" names a prerequisite source. However, it never says when to prefer this over search_inbox, which is the closest sibling, leaving the main routing decision to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Archive, undo archive, or set read state on a thread in the selected mailbox. Requires account write permission. Archive is recoverable using unarchive.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | ||
| threadId | Yes | ||
| emailAccountId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds real context beyond that: the write-permission requirement and the fact that archiving is recoverable via unarchive, which explains why destructiveHint is false. It omits idempotency behavior (e.g., archiving an already-archived thread) and the effect scope on the whole thread.
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, no filler, with the operation list front-loaded and the permission/recoverability caveats following. Every clause 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-required-param mutation tool with no output schema, the description covers the action set, the permission requirement, and reversibility of archive. It lacks detail on what happens for already-archived/read threads and whether the change spans the entire thread, but the coverage is close to sufficient.
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 carry parameter meaning. It does gloss the action values ('archive, undo archive, or set read state' mapping to archive/unarchive/read/unread), but gives no explanation of threadId or emailAccountId beyond their self-explanatory names. Partial compensation only.
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 names a specific resource (a thread in the selected mailbox) and enumerates the exact operations available: archive, unarchive, read, unread. This clearly separates it from siblings like read_mail/open_mail, since the verb is state mutation rather than retrieval. It stops short of explicitly naming which sibling to prefer, which holds it at a 4.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states a prerequisite ('Requires account write permission') and notes that archive can be reversed with unarchive, which implies when each action is appropriate. However, it never says when to use change_mail versus siblings like open_mail, read_thread, or search_inbox, so guidance is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a mailbox draft with a recipient, subject, and body. Saves the draft for review without sending email.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Recipient email address or comma-separated addresses. | |
| body | Yes | Draft body. Plain text is converted to HTML. This creates a mailbox draft and does not send. | |
| subject | Yes | ||
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as non-read-only but non-destructive and open-world; the description adds the important behavioral fact that no email is sent, confirming the side-effect boundary. It stops short of disclosing auth requirements, whether an existing draft is overwritten, or what identifier comes back.
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 tight sentences, front-loaded with the action and followed by the key constraint. No filler or repetition.
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 write tool with 5 parameters at 40% coverage and no output schema, the description is too thin: it never explains the role of emailAddress/emailAccountId nor what the caller gets back (e.g., a draft ID). An agent could invoke it but lacks the context to shape the request 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?
At only 40% schema description coverage, the description should compensate, but it merely restates the three required fields (to, subject, body) already covered by the schema and says nothing about emailAddress or emailAccountId. The ambiguous overlap between 'to' and 'emailAddress' is left completely unexplained.
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?
States a clear verb+resource ('Create a mailbox draft') and names the three fields it takes, so the core action is unambiguous. However, it does not differentiate itself from the sibling save_mail_draft, which an agent could easily confuse with this 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?
'Saves the draft for review without sending email' implies the use case (compose-but-don't-send) but never states when to prefer this over send_mail or save_mail_draft. Usage is inferable rather than explicit, and no exclusions or prerequisites are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create an automation rule for one inbox account.
| Name | Required | Description | Default |
|---|---|---|---|
| rule | Yes | ||
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the write/risk profile is covered. The description adds only the single-account scoping hint; it says nothing about irreversible side effects of rule actions (DELETE, SEND_EMAIL, CALL_WEBHOOK all appear in the schema), whether rules run retroactively on existing mail, or execution limits, which is significant for a tool with destructiveHint=true.
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 front-loaded sentence with no wasted words. It is efficient, though that efficiency is partly achieved by omitting content the tool's complexity calls for.
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 create tool whose schema contains nested conditions and a large action enum with destructive effects, and with no output schema and no parameter descriptions, the description is far too thin. An agent knows what it is for but not how to assemble a valid rule payload or what will happen when it runs.
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 all three parameters — including a deeply nested rule object with 16 action types, conditions, and delay/channel fields — are undocumented in structured data. The description must compensate but only implies that the rule belongs to one inbox account, leaving emailAddress vs emailAccountId and the rule payload structure unexplained.
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 has a specific verb and resource ('Create an automation rule') and adds scope ('for one inbox account'), so an agent can distinguish it from get_rule, list_rules, update_rule and delete_rule by name and text. It stops short of explicitly naming those siblings or the conceptual relationship between them, so it is clear but not maximally differentiated.
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?
There is no guidance on when to create a rule versus updating an existing one, nor any mention of prerequisites such as needing a valid inbox account. The phrase 'for one inbox account' hints at scoping but does not tell the agent which input field carries that account or that it is required.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete an automation rule for one inbox account.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds nothing beyond that — no irreversibility note, no auth/permission requirement, no behavior when the rule or account is unknown.
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 front-loaded sentence with no filler. It is efficient, though its brevity comes at the cost of the missing detail noted elsewhere rather than being a model of economical completeness.
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 destructive, non-read-only tool with 0% parameter documentation and no output schema, the description is too thin. An agent cannot tell which identifier actually selects the rule or whether the account parameters are required to disambiguate.
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% across three parameters, so the description carries the burden and fails: 'id' is never named or explained, and the presence of two additional account-identifying parameters (emailAddress, emailAccountId) alongside the required id goes unaddressed, leaving their relationship ambiguous.
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?
States a specific verb and resource ('Delete an automation rule') and adds a scope qualifier ('for one inbox account'). The delete verb distinguishes it from create_rule/get_rule/update_rule on its own, though it never names those siblings explicitly.
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 statement of when to use this versus update_rule, list_rules, or get_rule, and no prerequisites or warnings. The only guidance is the implicit 'delete means removal'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get response time analytics for one inbox account.
| Name | Required | Description | Default |
|---|---|---|---|
| toDate | No | ||
| fromDate | No | ||
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds the scoping constraint that results are per-account, but says nothing about what is measured, over what default window, or whether results are aggregated.
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 front-loaded sentence with no filler. It is efficient, though the brevity borders on under-specification rather than true concision.
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?
With no output schema, zero parameter descriptions and no annotations covering semantics, the description should explain what 'response time analytics' contains (e.g. averages, percentiles, time buckets). For a four-parameter analytics tool it leaves the agent guessing about inputs and outputs.
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% for four parameters, and the description mentions none of them. The phrase 'one inbox account' loosely implies a single account identifier relates to emailAccountId, but the epoch/units of fromDate and toDate and the relationship between emailAddress and emailAccountId remain completely unexplained.
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?
States a specific verb and resource ('Get response time analytics') scoped to 'one inbox account', which is more precise than the generic sibling get_stats_by_period. It does not explicitly contrast itself with that sibling, so it stops short of a 5.
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?
There is no when-to-use guidance, no mention of the closest alternative (get_stats_by_period), and no stated preconditions such as needing a valid email account. Usage can only be inferred from the phrase 'one inbox account'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get one automation rule by ID for one inbox account.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered without the description. The description contributes only the mild scoping detail that the lookup is bound to one inbox account, adding little beyond the structured fields.
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 short sentence with the verb and resource front-loaded, leaving no filler or redundancy to trim.
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-only lookup with annotations covering the safety profile and no output schema, the essentials of identifying the lookup target are present. It still omits what a rule record contains, error behavior for an unknown ID, and how the two account-scoping parameters interact.
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 carry the burden for three parameters. It partially does so: 'by ID' corresponds to the required id, and 'for one inbox account' gestures at the emailAddress/emailAccountId scoping pair, but it never explains how those two account parameters relate or which is authoritative.
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?
States a specific verb (get) and resource (automation rule) with singular scope, which implicitly separates it from list_rules and the create/update/delete_rule siblings. It never names those siblings explicitly, so the differentiation is inferable rather than stated.
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 phrase 'by ID' implies the precondition that you already hold an identifier, which is a usable usage cue. However, there is no explicit guidance on when to reach for get_rule versus list_rules or search, and no exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get email statistics grouped by day, week, month, or year.
| Name | Required | Description | Default |
|---|---|---|---|
| period | No | ||
| toDate | No | ||
| fromDate | No | ||
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds only the grouping dimension; it says nothing about what statistics are returned, how the date bounds are interpreted, or whether results are paginated/limited.
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 well-formed sentence with no filler, and the core purpose is front-loaded. It is efficient, though arguably under-specified rather than genuinely concise for a five-parameter 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?
With five mostly undocumented parameters, no output schema, and no explanation of filtering semantics or date units, the definition leaves substantial gaps an agent needs to call this correctly. The annotations carry the safety story, but the functional contract is 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?
Schema description coverage is 0% across 5 parameters, so the description must compensate and it does not. It restates the period enum already present in the schema, and leaves toDate/fromDate units (epoch seconds vs milliseconds?), emailAccountId, and the relationship between emailAddress and emailAccountId completely undefined.
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 states a specific verb (Get), resource (email statistics), and the grouping dimension (day/week/month/year), which is clear. It does not, however, distinguish itself from the sibling get_response_time_stats, which is also a stats-retrieval 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?
There is no guidance on when to use this tool versus get_response_time_stats or any other sibling, and no mention of prerequisites or filtering context. The agent is left to infer scope entirely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the inbox accounts linked to the authenticated user.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds the useful scoping note that results are limited to the authenticated user's accounts, but says nothing about pagination, ordering, or return shape beyond what annotations provide.
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 front-loads the action and resource with zero filler. Every word earns its place and nothing is repeated from the title.
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 listing tool with annotations and no output schema, the description is nearly sufficient: it establishes scope and implies no arguments. It could be complete with a note on pagination or ordering behavior, but that is a minor omission.
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 takes zero parameters, so the baseline is 4. The description correctly implies no input is needed by framing the listing as tied to the authenticated user, and there are no parameters whose semantics need clarifying.
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 states a clear verb ('List') and resource ('inbox accounts linked to the authenticated user'). It distinguishes from most siblings, which are mail-content operations rather than account enumeration. However, it doesn't explicitly call out the contrast with list_rules, the other list tool, so it falls just short of 5.
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 phrase 'linked to the authenticated user' implies the scope is the caller's own accounts and requires no arguments, which gives some context for when the tool applies. But it doesn't state when to use this rather than search_inbox or list_rules, nor does it mention any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List automation rules for one inbox account.
| Name | Required | Description | Default |
|---|---|---|---|
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds the scoping constraint that results are tied to a single inbox account, which is useful but not rich behavioral detail (no pagination, ordering, or volume 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?
It is a single front-loaded sentence with no filler. It is arguably too terse, but the terseness is captured under other dimensions rather than being wasted structure.
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 0% schema description coverage and no output schema, the one-line description leaves key unknowns: which account parameter to use, whether all rules are returned, and any ordering/pagination behavior. Annotations cover safety but not the operational details an agent needs.
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 both parameters (emailAddress, emailAccountId) are undocumented in the schema. The description only vaguely implies a single-account scope and never clarifies which identifier to supply or in what format, so it does not compensate for the coverage gap.
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 states a clear verb ("List") and resource ("automation rules") with a scope qualifier ("for one inbox account"). It implicitly distinguishes the tool from single-rule siblings like get_rule and mutating siblings like create_rule/delete_rule/update_rule, though it does not name them.
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?
There is no explicit when-to-use or when-not-to-use guidance, nor any named alternative. The only contextual hint is the phrase "for one inbox account," leaving the agent to infer when listing rules is appropriate versus calling get_rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Open the mail client to browse, read, compose, and organize linked mailboxes. Link an Inbox Zero account first. Does not change mail.
| Name | Required | Description | Default |
|---|---|---|---|
| threadId | No | Thread ID in the selected mailbox to open; omit to browse the inbox. | |
| emailAccountId | No | Linked mailbox ID from list_email_accounts; defaults to the first linked mailbox. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered; 'Does not change mail' merely restates it. The description does add the account-linking prerequisite, but says nothing about side effects of launching the client or what a threadId selection does behaviorally.
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?
Three tight sentences: purpose first, prerequisite second, read-only reassurance last. No padding, and the most important framing (what the tool opens) is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-required-parameter UI-launch tool with no output schema and full schema coverage on its two optional params, the description is nearly sufficient. The only gap is the absence of any hint about what invoking it produces (a client session/context) versus the data-returning siblings.
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 both threadId and emailAccountId are fully documented in the schema (including the note to use list_email_accounts). The description adds nothing beyond that, so the 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?
States a specific verb and resource ('Open the mail client') and enumerates the resulting capabilities (browse, read, compose, organize), so the agent knows this is a UI-launch entry point rather than a data operation. It does not, however, differentiate itself from close-sounding siblings like browse_mail or read_mail, which the agent must disambiguate on its own.
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?
'Link an Inbox Zero account first' gives a real prerequisite, which is useful. But there is no when-to-use guidance relative to the many siblings (browse_mail, read_mail, read_thread, search_inbox), so the agent must infer that this tool opens the client while those act within it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read a complete thread for the mail interface, including mailbox draft references. Use browse_mail to obtain its thread ID.
| Name | Required | Description | Default |
|---|---|---|---|
| threadId | Yes | ||
| emailAccountId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds a small amount of extra context by noting that draft references are included in the returned thread, but says nothing about pagination, size limits of a thread, or permission requirements.
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 short sentences, no filler, with the core verb-resource statement front-loaded. Slightly terse rather than bloated, which is the right failure mode for a simple two-parameter read 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?
For a read-only tool with annotations covering safety and no output schema, the essentials are mostly present. But with 0% schema coverage on two required parameters and no discussion of emailAccountId, an agent lacks enough to map account context confidently.
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 carry parameter meaning. It explains the origin of threadId (via browse_mail) but says nothing about emailAccountId, which is equally required and undocumented anywhere. Partial compensation only.
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 states a specific verb and resource ('Read a complete thread ... for the mail interface') with the notable addition of 'including mailbox draft references'. It clearly differentiates from browse_mail by implying browse_mail produces IDs while this consumes one, though it does not address the sibling read_thread, which an agent could easily confuse with this 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?
It gives explicit prerequisite guidance: 'Use browse_mail to obtain its thread ID', which tells the agent where the required input comes from. It does not, however, state when this tool should be preferred over the similarly named read_thread, leaving one real ambiguity unresolved.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read messages from one inbox thread by thread ID. Returns plain-text bodies truncated per message.
| Name | Required | Description | Default |
|---|---|---|---|
| threadId | Yes | Thread ID from search_inbox. | |
| maxMessages | No | ||
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral detail about the return format ('plain-text bodies truncated per message'), but says nothing about auth requirements or pagination 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?
Two short, front-loaded sentences with no wasted words. The core action is stated first and the return-format note follows.
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 read-only tool with no output schema, the description reasonably covers the return format. However, with three of four parameters undocumented, an agent lacks the semantics needed to use maxMessages, emailAddress, or emailAccountId 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 only 25%: only threadId is documented (via the schema itself), while maxMessages, emailAddress, and emailAccountId are undocumented in both schema and description. The description does not compensate for this gap.
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?
States a specific verb and resource: 'Read messages from one inbox thread by thread ID.' This is clear, but it doesn't explicitly distinguish itself from siblings like read_mail or search_inbox, so the agent must infer the difference.
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 when-to-use or when-not guidance is given. The only routing hint is buried in the schema ('Thread ID from search_inbox'), and the description never states when to prefer this over read_mail or open_mail.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create or update a mailbox draft for review; never sends. Body is plain text. Use replyToMessageId from read_thread to thread a reply. Use its returned draftId for subsequent edits. Requires account write permission.
| Name | Required | Description | Default |
|---|---|---|---|
| cc | No | ||
| to | Yes | ||
| body | Yes | ||
| draftId | No | ||
| subject | Yes | ||
| emailAccountId | Yes | ||
| replyToMessageId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnly=false, destructive=false, openWorld=true. The description adds genuinely useful behavior: this never sends, the body must be plain text, write permission is required, and the draftId is the handle for subsequent edits. That goes meaningfully beyond the annotation set 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?
Three compact clauses with the most important constraint ('never sends') front-loaded, followed by parameter sourcing and auth requirements. No filler sentences.
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 7-parameter mutation tool with no output schema, the description covers the critical behaviors, permission requirement, and even the returned draftId handle. Remaining gaps are minor field-level details like cc formatting and account selection.
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 schema documents nothing. The description compensates for the two highest-value parameters (replyToMessageId, draftId) with sourcing and reuse semantics, and constrains body to plain text, but leaves to, cc, subject, and emailAccountId unexplained.
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?
States a specific verb (create or update) and resource (mailbox draft) and immediately disambiguates from the sending sibling with 'never sends'. An agent can distinguish this from send_mail and create_draft without opening a schema.
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?
Gives clear context: use for drafts kept for review, thread replies via replyToMessageId from read_thread, reuse the returned draftId for edits, and requires account write permission. It names the source of inputs and the follow-up path but does not explicitly say when to prefer this over a sibling like create_draft.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search one inbox and return message metadata and snippets. Does not return full message bodies, send email, or change mail.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query using the mailbox provider's search syntax (Gmail or Outlook). | |
| pageToken | No | ||
| maxResults | No | ||
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that by specifying the result granularity ('metadata and snippets', not full bodies). It is silent on pagination behavior despite a pageToken parameter existing.
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 short sentences, zero filler, with the positive capability stated before the exclusions. Nothing needs to be trimmed and nothing is buried.
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 five-parameter, paginated search tool with no output schema, the description usefully characterizes the return payload but omits the parameter semantics that the schema leaves undocumented. Adequate but with a clear gap around the account-selection and paging 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 description coverage is only 20% – just 'query' is documented. The description hints that an inbox must be selected ('one inbox') but never explains emailAddress vs emailAccountId, maxResults (capped at 20), or pageToken. With four undocumented parameters, the description does not compensate for the coverage gap.
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?
States a specific verb and resource ('Search one inbox') plus the return shape ('message metadata and snippets'), and scopes the resource with 'one'. It implicitly separates itself from read_mail by denying full bodies, but never names a sibling alternative explicitly.
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 negative clauses ('Does not return full message bodies, send email, or change mail') effectively route the agent away from read_mail, send_mail and change_mail, which is genuine when-not guidance. It does not, however, state when this tool is the right choice over browse_mail or how to pick the target inbox.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send email using the connected application’s mcp:send capability. The mail client UI asks the user to confirm recipients and content before invoking this tool; callers must obtain that confirmation. Body is plain text. Reuse mutationId, queuedAt, and the exact payload on retries to avoid duplicate sends. An uncertain result must be reconciled in Sent before another send. Requires mcp:send permission.
| Name | Required | Description | Default |
|---|---|---|---|
| cc | No | ||
| to | Yes | ||
| body | Yes | ||
| draftId | No | ||
| subject | Yes | ||
| queuedAt | Yes | ||
| mutationId | Yes | ||
| emailAccountId | Yes | ||
| replyToMessageId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructiveHint=true and openWorldHint=true, and the description goes well beyond them: it names the required mcp:send permission, documents idempotency semantics to avoid duplicate sends, and specifies that the body is plain text only. The duplicate-send and reconciliation warnings are meaningful risk disclosures annotations cannot carry.
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?
Five tight sentences, front-loaded with the action, then prerequisites, then retry safety. No filler and every clause carries operational information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a destructive, open-world mutation with no output schema and 9 mostly undocumented parameters, the description covers confirmation flow, permissions, idempotency, and recovery from uncertain results. The notable remaining gap is that no field-level format or recipient-list syntax is given for the six required identifiers/addresses.
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% across 9 parameters, so the schema itself says nothing about what each field means. The description partially compensates by explaining mutationId and queuedAt (retry/idempotency keys) and the body's plain-text constraint, but leaves emailAccountId, to, cc, subject, draftId, and replyToMessageId entirely unexplained.
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?
States a specific verb and resource ('Send email') and scopes the mechanism ('mcp:send capability'), which is unambiguous against draft-oriented siblings like create_draft and save_mail_draft. An agent can tell this performs an actual send rather than a draft mutation.
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?
Explicit preconditions (user confirmation of recipients and content must already be obtained) plus concrete retry rules: reuse mutationId, queuedAt, and the exact payload on retries, and reconcile an uncertain result in Sent before sending again. This is exactly the when/how guidance a send tool needs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Replace an automation rule for one inbox account.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| rule | Yes | ||
| emailAddress | No | ||
| emailAccountId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description adds one genuine behavioral fact — 'Replace' implies full overwrite of the rule object rather than a merge — but says nothing about permissions, side effects of the replace, or what happens to omitted fields.
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 front-loaded sentence with no filler or redundancy. It is efficient, though its brevity is a consequence of under-specification rather than disciplined editing.
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 destructive mutation with a large nested payload, no output schema, and zero schema description coverage, one sentence is far too thin. An agent gets no help on required field semantics, replacement behavior, or error conditions.
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% across four parameters, including a deeply nested 'rule' object with 16 action enum values. The phrase 'one inbox account' faintly gestures at emailAccountId/emailAddress but provides no clarifying meaning for id or the rule structure.
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 gives a specific verb ('Replace') and resource ('automation rule') scoped to 'one inbox account'. The word 'Replace' usefully signals full-overwrite semantics rather than a partial patch, but no sibling (create_rule, delete_rule, get_rule) is named to disambiguate.
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 when-to-use guidance and no alternatives are offered, despite four closely related siblings (create_rule, delete_rule, get_rule, list_rules). The only inference available is that an existing rule must exist to be replaced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
create_draft1 field changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"create_rule6 fields changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"Input schema / properties / rule / properties / actions / items / properties / fields / anyOfPrevious value: -[
- {
- "properties": {
- "bcc": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "cc": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "content": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "folderName": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "label": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "subject": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "to": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "webhookUrl": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- }
- },
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "properties": {
+ "bcc": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "cc": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "content": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "folderName": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "label": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "subject": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "to": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "webhookUrl": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / rule / properties / actions / items / properties / messagingChannelId / anyOfPrevious value: -[
- {
- "format": "cuid",
- "pattern": "^[cC][^\\s-]{8,}$",
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "format": "cuid",
+ "pattern": "^[cC][0-9a-z]{6,}$",
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / rule / properties / condition / properties / aiInstructions / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Input schema / properties / rule / properties / condition / properties / aiInstructions / typeAdded value: +[
+ "string",
+ "null"
+]Input schema / properties / rule / properties / condition / properties / static / anyOfPrevious value: -[
- {
- "properties": {
- "from": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "subject": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "to": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- }
- },
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "properties": {
+ "from": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "subject": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "to": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]delete_rule1 field changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"get_response_time_stats1 field changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"get_rule1 field changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"get_stats_by_period1 field changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"list_rules1 field changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"read_thread1 field changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"search_inbox1 field changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"update_rule6 fields changedInput schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"Input schema / properties / rule / properties / actions / items / properties / fields / anyOfPrevious value: -[
- {
- "properties": {
- "bcc": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "cc": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "content": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "folderName": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "label": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "subject": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "to": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "webhookUrl": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- }
- },
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "properties": {
+ "bcc": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "cc": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "content": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "folderName": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "label": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "subject": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "to": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "webhookUrl": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / rule / properties / actions / items / properties / messagingChannelId / anyOfPrevious value: -[
- {
- "format": "cuid",
- "pattern": "^[cC][^\\s-]{8,}$",
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "format": "cuid",
+ "pattern": "^[cC][0-9a-z]{6,}$",
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / rule / properties / condition / properties / aiInstructions / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Input schema / properties / rule / properties / condition / properties / aiInstructions / typeAdded value: +[
+ "string",
+ "null"
+]Input schema / properties / rule / properties / condition / properties / static / anyOfPrevious value: -[
- {
- "properties": {
- "from": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "subject": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "to": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- }
- },
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "properties": {
+ "from": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "subject": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "to": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]browse_mailchange_mailcreate_draftcreate_ruledelete_ruleget_response_time_statsget_ruleget_stats_by_periodlist_email_accountslist_rulesopen_mailread_mailread_threadsave_mail_draftsearch_inboxsend_mailupdate_ruleSearch connected email, read and manage messages, draft and send, and manage rules for new mail.
Manage Gmail end-to-end: search, read, send, draft, label, and organize threads. Automate workflow…
Read and search FranklyMail email and prepare drafts, replies, and forwards for human approval.
Read, send, file and search email in any Gmail, Microsoft 365 or IMAP mailbox, plus its calendar.
Add one secure layer between your agents and this server.