Skip to main content
Glama
Sign In
Uoink

Uoink

by ryanbiddy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Write tweet or thread

write_tweet

Prepare tweet or thread grounding, or save an agent-written credited draft with Voice DNA checks; optionally generate directly via Anthropic key without posting to social accounts.

Instructions

Prepare grounding for a tweet or thread, or save a credited draft in the local Writing Studio. Use for short social drafts; use write_blog for articles or generate_script for video scripts. Without body, returns grounding unless direct generation is requested with the saved Anthropic key. With body, saves the agent's draft and returns soft Voice DNA warnings. Creator credit cannot be suppressed. Direct generation sends context to Anthropic and retries fatal phrase violations once before refusing to save; nothing is posted to a social account.

Input Schema

NameRequiredDescriptionDefault
bodyNoAgent-written draft text, including mandatory source credit; omit for grounding or explicitly requested direct generation.
kindNoDirect-generation output kind.
tagsNoFree-form labels to attach to the saved item or draft.
angleNoRequested editorial focus for the draft's grounding or direct-generation prompt.
generateNoWhen true and body is absent, generate directly with the saved Anthropic key.
parent_idNoEarlier writing-piece ID to link as this draft's parent version.
output_modeNoComposer output mode. thread prompts a thread while persisting a tweet-kind piece (the composer splits the body).
compute_modeNoUse byo_key to request direct generation.
hook_type_lensNoOptional hook lens that biases the opening toward that style (generation intent).
source_yoink_idNoSaved item to ground the draft and creator credit; omit for a draft without a source item.
suppress_creditNoMust not be true: suppressing creator credit is rejected.
style_anchor_idsNoSaved style-reference IDs from list_style_anchors to include in writing context.
source_credit_lineNoExact creator-credit line to retain in the body; use the line supplied by grounding.
target_length_charsNoDesired character length for the writing prompt; not a hard persistence limit.
skip_voice_dna_this_timeNoSkip the Voice DNA check for this save; does not waive mandatory source credit.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.12.1

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, it discloses that nothing is posted to a social account, creator credit cannot be suppressed, direct generation sends context to Anthropic, fatal phrase violations are retried once, and the tool then refuses to save. These are meaningful behavioral traits not covered by readOnlyHint/openWorldHint/destructiveHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action and alternatives, then moves through mode behavior and constraints in a compact sequence. Despite covering a complex tool, every sentence contributes to correct invocation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter mutation tool with no output schema, the description supplies the critical mode distinctions, safety constraints, and generation behavior an agent needs to call it correctly. The remaining details are well covered by the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds useful meaning to the main workflow parameters by explaining body presence/absence, direct generation, saved drafts, Voice DNA warnings, and the non-suppressible credit constraint, though it does not interpret every optional parameter beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: preparing grounding for, or saving a credited draft of, a tweet or thread in the local Writing Studio. It explicitly distinguishes itself from write_blog and generate_script, so an agent can identify the correct tool without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It says to use this for short social drafts and names the alternatives for articles and video scripts. It also explains the key branching conditions: without body returns grounding, with body saves the draft, and direct generation only happens when explicitly requested.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools