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

Annotations only declare the generic write-profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false). The description adds genuinely new behavior: a draft is created but never published, no tool in this server publishes, and the return value contains review_url that the agent must relay to the user. It stops short of stating whether repeat calls create duplicate drafts, which matters given idempotentHint=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?

Front-loaded with the trigger and the critical 'saves a DRAFT' caveat, then parameters, then the return-value instruction, then exclusions — a sensible order. Slightly dense by necessity, though the parenthetical 'X is coming soon' and the trailing 'Free.' are minor filler.

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?

A five-parameter write tool with zero schema descriptions and an output schema; the description compensates by documenting every parameter, the draft-only guarantee, the per-platform calling convention, and how to act on the returned review_url. Nothing an agent needs to invoke it correctly 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 description coverage is 0%, so the description carries the full burden and does so for all five parameters: platform values plus aliases ('Shorts', 'Reels', 'IG') and the X exclusion, clip_id and account_id provenance (list_clips, list_social_accounts), caption's 2,200-character limit, and scheduled_at's ISO 8601-with-offset format including a concrete example.

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 ('RipClip saves a DRAFT') with the crucial scope boundary that it never publishes or schedules. The 'Not for:' clause names the sibling tools (write_captions, plan_posts, update_draft) so an agent can disambiguate without opening any schema.

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?

Opens with a when-to-use trigger plus three quoted user utterances that map natural language onto the tool. Explicitly excludes four adjacent tasks and routes each to the correct alternative, and adds the 'one call per platform' procedural rule.

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