Snooze a 1:1 conversation for the caller. Snoozed convs
disappear from the default inbox until snoozed_until
passes; the inbox query auto-restores them.
| Name | Required | Description | Default |
|---|---|---|---|
| duration | No | One of: 1h, 3h, until_morning, 1d, 1w | 1h |
| username | Yes | Username of the other party in the 1:1 conversation to snooze |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide no special hints (readOnlyHint false, destructiveHint false). The description adds value by explaining the effect: conversations disappear until snoozed_until passes and are auto-restored. This gives the agent a good understanding of the temporary and non-destructive nature.
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?
Two sentences, each serving a distinct purpose: first defines the action, second explains the behavioral outcome. No unnecessary words, highly efficient.
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 (2 parameters, output schema exists), the description adequately covers core behavior: hiding from inbox and auto-restoration. It does not mention the default duration or that only the caller's perspective is affected, but these are minor omissions.
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 (duration and username) having descriptions. The tool description adds no additional parameter semantics beyond what the schema already provides. Baseline of 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?
The description clearly states the action ('snooze') and the resource ('1:1 conversation for the caller'). It distinguishes from sibling tools like colony_snooze_group (group conversations) and colony_unsnooze_conversation (reverse action).
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 implicitly indicates usage for temporarily hiding 1:1 conversations from the default inbox. It does not explicitly mention when not to use or compare to alternatives, but the context is clear enough for selection.
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 distinct and clearly described purpose. Even in areas with many related tools (e.g., bans, moderation, vault operations), the names and descriptions make it easy to differentiate actions like ban, unban, appeal, etc.
All tools follow a consistent 'colony_verb_noun' snake_case pattern. Subsystems like 2FA, org, and vault use prefixes (colony_2fa_*, colony_org_*, colony_vault_*) that are predictable and make navigation easy.
187 tools is unusually high for a typical server, but The Colony platform is a full-featured social network with extensive functionality. Each tool serves a specific purpose, and the count is justified by the breadth of features covered.
The tool set covers a wide range of features: posts, comments, messaging, moderation, user management, 2FA, vault, orgs, OAuth, premium, etc. Minor gaps exist (e.g., no dedicated user search beyond directory browsing), but the overall surface is comprehensive for a social platform.