Start connecting a new social account. For OAuth providers this returns an authorizeUrl the user must open in a browser. Telegram requires botToken and chatId; Discord requires webhookUrl.
| Name | Required | Description | Default |
|---|---|---|---|
| chatId | No | Telegram chat target, e.g. @yourchannel (telegram only). | |
| botToken | No | Telegram bot token (telegram only). | |
| provider | Yes | Provider to connect. | |
| webhookUrl | No | Discord channel webhook URL (discord only). |
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?
There are no annotations, so the description carries the full burden. It discloses the OAuth authorizeUrl behavior and the required inputs for Telegram and Discord, but does not elaborate on side effects (e.g., whether the connection is immediately active), authentication requirements for the tool itself, or error scenarios.
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 main action, and no unnecessary detail. Every clause adds information about the connection flow or provider requirements.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description adequately covers the main flows and provider-specific requirements. The lack of an output schema is partially mitigated by mentioning the authorizeUrl return for OAuth, but it does not explain the return value for Telegram/Discord or describe the overall connection lifecycle.
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 already has 100% coverage with descriptions for each parameter. The description adds provider-dependent parameter semantics, noting that botToken/chatId are needed for Telegram and webhookUrl for Discord, which goes beyond the individual property descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource ('Start connecting a new social account') and clarifies the tool's role relative to siblings like list_accounts and account_capabilities. It also mentions provider-specific behaviors (OAuth authorizeUrl, Telegram/Discord parameters), which further distinguishes the tool's purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explains when to use the tool (to start connecting a new account) and provides conditional guidance: OAuth providers require a browser authorization step, while Telegram and Discord take specific parameter sets. However, it stops short of explicitly naming alternative tools or stating when not to use it.
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.
Most tools have clearly distinct purposes, but a few are close: delete_instagram_comment vs hide_instagram_comment overlap (though one is preferred), and get_analytics overlaps with Instagram-specific analytics tools. Overall, the boundaries are generally clear, with only minor potential confusion.
All tool names follow a consistent snake_case verb_noun pattern (e.g., list_accounts, connect_account, upload_asset, cancel_post). There are no deviations in style or grammar, making the naming highly predictable.
With 31 tools, this exceeds the 25-tool threshold for 'too many'. While the broad multi-provider social media domain justifies some breadth, the sheer number makes the surface heavy and potentially overwhelming, pushing the score down.
The tool set covers core workflows well: account connection, scheduling/publishing, post management, analytics, Instagram-specific engagement (comments, messages), asset upload, and workspace health/usage. Minor gaps include no explicit disconnect_account or delete_post, but these are edge cases; the domain is largely covered.
