get_base_apitools_sendDMSV2sendDMSV2 Group: DMS. Billing per call: 1 Credits.
| Name | Required | Description | Default |
|---|---|---|---|
| ct0 | No | ||
| text | No | ||
| apiKey | No | ||
| media_id | No | media_id from [uploadMediaDM] | |
| proxyUrl | No | ||
| resFormat | No | ||
| auth_token | No | ||
| request_id | No | ||
| recipient_ids | No | ||
| conversation_id | No |
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?
With no annotations provided, the description carries the full burden of behavioral disclosure, but it reveals nothing about side effects, authentication requirements, expected behavior, or required context. Sending a DM likely involves account actions, but the description does not disclose anything beyond the tool name.
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 short, but this is under-specification rather than conciseness. 'Group: DMS' and 'Billing per call' add no functional value, and the essential purpose is missing.
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?
This is a 10-parameter DMS-sending tool with no annotations, no output schema, and almost no parameter documentation. The description completely fails to provide the contextual information needed for an agent to invoke this 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 description coverage is only 10%, with 10 parameters and zero required. The description adds no meaning to any parameter, leaving the agent to guess what fields like ct0, resFormat, proxyUrl, or recipient_ids actually mean.
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 merely restates the tool name ('sendDMSV2') and category ('Group: DMS'), but never explicitly states that it sends a direct message. It provides no meaningful verb-resource clarity and does not distinguish it from sibling tools like sendDMS or sendDMSMedia.
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 alternatives such as sendDMS, sendDMSMedia, or getUpdateDMSV2. The description only mentions billing, which is irrelevant to usage context.
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 set is full of confusing variants such as get_/post_ prefixed duplicates of the same endpoints, competing V1/V2 versions of the same action (e.g., followersList vs. followersListV2), and poorly described tools like CommunitiesSearchV2 and getCt0 that give no clear unique purpose. Agents would frequently need to guess between similar tools for a single task.
Naming is chaotic, mixing camelCase (getDMS, likeV2), PascalCase (CreateNoteTweet, CommunitiesMemberV2), and inconsistent prefixes (gettools_*, get_*, post_*) with duplicated operations. The 'get_/post_' prefixes appear to indicate API method rather than action, but they are applied inconsistently, with some tools appearing under both and others only once. There is no predictable verb_noun pattern throughout.
With 107 tools, the server is extremely large, far exceeding the 50+ threshold for extreme mismatch, and this count is inflated by duplicates (many get_/post_ twins) and overlapping V1/V2 variants. Even the unique tool set is likely around 60-70, which is still an unwieldy surface for an agent to negotiate. This severely disrupts coherence.
The tool set covers most core Twitter/X domains: tweets, likes, retweets, follows, DMs, search, communities, lists, and profile management. However, it is cluttered with duplicates and lacks some obvious pieces like mute/unmute operations or a direct 'update tweet' action, and several tools appear to be thin wrapper variations of the same endpoint. Coverage is broad but not cleanly organized.