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

Goes far beyond the annotations by disclosing several non-obvious failure-causing behaviors: X/Twitter strips full URLs AND bare domains from captions (with the pricing rationale), is_draft only saves in Post Bridge and publishes immediately when later sent, and platform_configurations.tiktok.draft is a distinct native-draft option. No contradiction with readOnlyHint=false or destructiveHint=true; the description strengthens the agent's mental model of a destructive, open-world operation.

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?

Roughly 200 words with zero filler. Core purpose is front-loaded, followed by prerequisites, then two critical warnings clearly flagged with 'IMPORTANT' and 'Note.' Every sentence carries actionable information appropriate to a 10-platform tool, and no sentence merely restates the name or schema.

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 a tool with 9 parameters, deeply nested per-platform overrides, 10 platforms, and no output schema, the description covers the non-obvious operational behaviors an agent cannot infer: immediate vs scheduled posting, public media URL download, X link removal, and the two distinct draft concepts. The exhaustive per-platform schema fills the remaining detail, so nothing needed for correct invocation is missing.

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 the schema already documents every parameter in depth (baseline 3). The description still adds interpretive meaning: cross-posting explains the multi-account semantics of social_accounts, the X/Twitter link-stripping warning attaches behavior to the caption parameter, and the is_draft versus tiktok.draft clarification resolves a confusion the schema alone could not.

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 ('publish or schedule'), resource ('social media post'), and exhaustively enumerates the 10 supported platforms, making the scope unmistakable. It also discloses the cross-posting capability up front, which clearly differentiates it from siblings like update_post (modify existing), upload_media (upload files), and list_posts (read).

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 concrete preconditions: 'Use list_social_accounts first to get account IDs' and 'Omit scheduled_at to post immediately,' plus platform-specific guidance on X/Twitter links and the is_draft/tiktok.draft distinction. However, it never explicitly names alternatives or exclusions (e.g., 'to modify an existing post, use update_post'), so some routing decisions are left to inference.

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