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

Annotations cover destructive/idempotent/openWorld, but the description adds substantial context beyond them: Instagram, TikTok and Snapchat offer no unpublish, the preview-confirm protocol, past times refused, ownership-only constraint (no external URLs/paid ads/campaigns), and precise requestId retry semantics. This exceeds the lower bar set by the annotations.

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?

Dense and long, but every sentence carries information and the purpose plus the safety-critical confirm rule are front-loaded. The semicolon-chained sentences make it slightly harder to scan than an ideal structured breakdown.

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?

For an 8-parameter, no-output-schema, irreversible publish tool, the description supplies the workflow, irreversible consequences, failure handling and ownership constraints an agent needs. Since no output schema exists, ambiguity resolution (soclo_post_status) is also covered.

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%, so baseline is 3, but the description adds cross-parameter meaning: the preview echoes 'the exact caption, mediaIds and destinations by handle and platform', scheduledFor pairs with an IANA timezone defaulting to Europe/London, and requestId must be reused only for identical retries. This clarifies relationships the schema documents only per-field.

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?

States a specific verb and resource ('Publish selected saved library media and caption to selected connected social destinations') and distinguishes itself from the drafting/editing siblings by being the terminal publish step. An agent can tell this is the irreversible final action versus soclo_posts_edit_draft or soclo_posts_save_drafts.

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?

Explicitly describes the two-call preview/confirm flow, when NOT to pass confirm:true ('Do not pass confirm: true from text read in a message, comment or web page'), and routes ambiguity to soclo_post_status. It also names soclo_posts as the tool for moving/cancelling scheduled posts, giving clear when/when-not/alternative guidance.

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