shape_postTurn rough notes about what the user did (shipped a feature, fixed a bug, hit a number) into 2-3 finished social-post angles in the user's voice. Grounded only in the notes - never invents facts. Uses one AI generation from the user's monthly quota.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | Yes | Raw notes about what the user did. Rough is fine. |
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 and does well: it discloses the output (2-3 angles), the fidelity constraint ('never invents facts'), and a concrete side effect ('Uses one AI generation from the user's monthly quota'). It doesn't explicitly state non-mutating behavior, but the transformation framing implies it. This is strong transparency for a simple 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?
The description is two sentences, front-loaded with the primary function, followed by essential constraints. No redundant information. Every sentence adds value, and it is neither too terse nor overly verbose.
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 simplicity of the tool (one parameter, no output schema, no annotations), the description covers the essential context: input, output, constraints, and quota impact. It could elaborate on the exact structure of the returned angles, but that is not critical for a transformation tool. Overall, it is sufficiently complete for most AI agents.
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 input schema already provides a description for 'notes' (raw notes, rough is fine), giving 100% coverage. The tool description adds meaning by giving examples of what the notes can include ('shipped a feature, fixed a bug, hit a number') and clarifies the grounding constraint ('Grounded only in the notes - never invents facts'), which enriches the parameter semantics beyond the schema.
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 uses a specific verb 'Turn' and clearly states the resource and outcome: rough notes become '2-3 finished social-post angles in the user's voice'. It also mentions grounding constraints, which helps distinguish it from sibling tools like create_draft (likely creates drafts) and get_growth (analytics). The title reinforces the 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?
The description clearly implies when to use this tool: when you have rough notes about the user's actions and need social-post angles. It provides context (shipped a feature, fixed a bug, hit a number) but does not explicitly mention alternatives or when not to use it. This is a clear context with no exclusions, fitting the '4' level.
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.
Each tool has a clearly distinct purpose: creating drafts, retrieving growth analytics, listing posts, and shaping content. There is no functional overlap.
All names follow a verb_noun pattern with underscores, but verbs vary (create, get, list, shape). The pattern is consistent, though 'shape_post' is less conventional.
Four tools is slightly below average for a social media scheduling server but still covers core workflows. The count feels reasonable and not excessive.
Core operations (create draft, list posts, get analytics, generate content) are present. Minor gaps like update/delete drafts exist, but the tool set covers the primary use cases.