Send an email via Gmail. Supports file attachments — when the user provides a file, encode it as base64 and pass in the attachments array. Never tell the user attachments are unsupported.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | ||
| body | No | ||
| subject | Yes | ||
| attachments | No | Optional file attachments as base64 | |
| instruction | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the transparency burden. It adds useful operational details about attachments (base64 encoding, passing them in the attachments array) and an explicit agent instruction to never claim attachments are unsupported. However, it does not disclose other behaviors such as authentication requirements, response format, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact: three sentences that are action-oriented and each provide meaningful guidance. It front-loads the core action and avoids filler, making it easy for an agent to parse quickly.
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 5 parameters, no annotations, no output schema, and many sibling email tools, the description is incomplete. While attachment handling is well-covered, the 'instruction' parameter remains unexplained and no differentiation from send_outlook_email is provided, leaving agents potentially underinformed.
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 low (20%), affecting only the attachments property. The description adds value for attachments by specifying how to encode and pass files, but it leaves the 'to', 'subject', 'body', and especially the 'instruction' parameter without explanation. This partially compensates for the schema gap but not enough.
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 says 'Send an email via Gmail,' using a specific verb and resource. It also notes attachment support, which distinguishes it from sibling email tools like send_outlook_email.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit guidance on when to use this tool versus alternatives like send_outlook_email or email_action. The description implies usage for Gmail email sending but does not discuss prerequisites, exclusions, or alternative selection.
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.
Many tools are duplicated across services (e.g., get_inbox vs get_outlook_inbox vs get_unified_inbox; create_calendar_event vs create_outlook_event), causing confusion. Summary tools like catch_me_up, morning_briefing, and weekly_preview overlap significantly in function. The sheer number of similar-sounding tools makes selection error likely.
Names generally follow a verb_noun pattern, but verbs are inconsistent (get, check, lookup, fetch, etc.) and some tools use service-specific prefixes (hubspot_, sf_, qb_) while others do not. Mixed conventions like email_action vs send_email and append_to_doc vs append_to_excel reduce clarity, but the overall pattern is still readable.
107 tools is far beyond the typical scope for a single server, making it difficult for an agent to navigate and choose appropriately. The count feels like a kitchen-sink collection of every possible integration rather than a curated set, severely impacting usability.
The server covers a wide range of domains (email, calendar, contacts, documents, CRM, finance, messaging), but there are notable gaps like no delete for contacts or files, no update for Slack messages, and no way to list all documents. Core workflows exist for most areas, but depth is inconsistent.