attachments.delete_bulkDelete several attachments of one email at once.
| Name | Required | Description | Default |
|---|---|---|---|
| ids | Yes | Attachment IDs to delete | |
| mailId | Yes | Mail ID | |
| mailboxId | Yes | Mailbox ID |
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| http_status | Yes | HTTP status of the API response |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already carry the important behavioral facts: destructiveHint=true, readOnlyHint=false, idempotentHint=false. The description adds only the scope constraint ('of one email at once') and does not describe behavior beyond what the annotations communicate, such as error handling or whether deletion is permanent. There is no contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with no filler. Every word contributes meaning, and the key distinction ('several,' 'one email,' 'at once') is front-loaded. Nothing needs to be cut or reordered.
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 three-parameter bulk-delete tool, the description is sufficient: schema documents all parameters, output schema exists, annotations cover destructive behavior, and the wording explains the operation's scope. An agent has everything it needs to invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds real semantic value by binding the three parameters together: 'several' maps to the ids array and 'one email' expresses the relationship between mailboxId and mailId, which helps an agent correctly group all attachment IDs under a single email.
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 the exact verb-resource pair ('Delete ... attachments') and adds three discriminating qualifiers: 'several,' 'of one email,' and 'at once.' This makes it easy for an agent to distinguish from the single-delete sibling attachments.delete and from delete tools on other resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies the intended use — deleting more than one attachment belonging to the same email — but it never states when to prefer this over attachments.delete for a single attachment, nor does it mention any exclusions or conditions. The usage context is recoverable from the wording, but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The resource namespaces make most tools easy to tell apart, and each action has a clear target. A couple of boundary cases exist, such as attachments.add versus mails.inject, since both relate to putting files on a simulated email, but descriptions mostly resolve the ambiguity.
Every tool follows the same resource.action convention, and the action verbs are predictable across the set, including delete_bulk and rotate_secret. The pattern is uniform even across different resource families, making the API very predictable.
With 40 tools, the surface is quite large for an MCP server, even though the namespaces are clean. Many singular and bulk delete variants could be combined or expressed as parameters to reduce the count, so the set feels heavier than it needs to be.
The server covers the main lifecycle needs for mailboxes, emails, attachments, archived mailboxes, domains, identities, OAuth clients, and team management. Minor gaps remain, such as no mailbox update/rename, no manual archive action, and no invitation acceptance endpoint, but agents can work around these.