Replace a drafted marketing output's body before it is shipped. Manual replacement only: the AI redraft stays in the app. A draft carrying an unfilled placeholder or a broken link is refused, and the previous draft is kept as revision history. Free; requires the 'act' scope and Founder tier.
| Name | Required | Description | Default |
|---|---|---|---|
| draft | Yes | The replacement draft body, 1 to 20000 characters. | |
| output_id | Yes | Output id (uuid), from list_outputs. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description discloses valuable behavioral traits: refusal of placeholders/broken links, retention of previous draft as revision history, and requirements (free, 'act' scope, Founder tier). These go beyond annotations and align with them (annotations: readOnlyHint false, destructiveHint false).
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?
Description is four concise sentences, each adding value: purpose, manual-only constraint, refusal conditions/revision history, and requirements. No redundant or filler content.
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?
Covers purpose, constraints, behavior, and auth requirements for a simple 2-parameter tool. Lacks mention of return value or success/error response, which would be helpful given no output schema, but the description is otherwise complete.
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% with both parameters fully described in the input schema. Description adds no additional parameter-level meaning beyond what schema already states, so baseline 3 is appropriate.
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?
Description clearly states 'Replace a drafted marketing output's body' with a specific verb and resource, and adds 'before it is shipped' for scoping. It differentiates from sibling update_draft by explicitly saying 'Manual replacement only: the AI redraft stays in the app.'
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?
Provides clear context: tool is for manual replacement before shipping, and implies not for AI-generated drafts. However, it does not name alternative tools or provide explicit when-not-to-use conditions beyond refusing placeholders/broken links.
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 follow a clear action+resource pattern (get_, list_, set_, ship_, etc.) with distinct purposes. A few boundaries could cause confusion, such as get_move vs get_output (both return drafts) and ship_move vs set_output_status (both mark things shipped), though descriptions mitigate this sufficiently.
The overwhelming majority use consistent snake_case verb_noun naming (list_feed, ship_move, get_visibility). The only outlier is 'whoami', a common convention but not verb_noun; otherwise the pattern is highly predictable.
At 41 tools, the surface is well over the 25-tool threshold for 'too many'. While the domain is broad, this volume places significant cognitive load on agents and suggests some consolidation or modularization could help.
Core workflows for moves and outputs are covered (create/list/get/update/ship/skip/undo). However, the tool descriptions reference 'approve_output' as the publishing action, yet that tool is absent from the list, leaving a dead end for channel distribution. There are also no tools for editing competitors or managing Memory pages beyond recording insights.