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

Adds substantial context beyond the annotations: nothing is published until approve_plan_posts, it consumes the user's AI credits, it blocks for tens of seconds to minutes, and a timeout does not mean failure. The annotations only say non-read-only, non-destructive, non-idempotent; the description explains the practical consequences that matter. It stops short of saying whether a failed call still burns credits.

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 purpose and then the safety-critical constraint (nothing published, credits consumed) before latency and recovery advice. Dense but every sentence carries operational value; the heavy capitalization and long final run-on of follow-up tools cost it a point on polish, not on length.

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 12-parameter, blocking, credit-consuming generation tool with no output schema, the description covers what is produced (captions, themes, image scenes), the review-gated state, cost, latency and failure recovery. Only the credit-cost-per-post and what happens to a partially written plan are left implicit.

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 75% with enums and defaults documented for days, tone, frequency, timezone, start_date, account_ids and social_group_id. The description reinforces the social-group scoping ('ONE social group') and that post count should be surfaced to the user, but adds almost no new per-parameter meaning. Baseline 3 fits given the schema does the heavy lifting.

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?

Specific verb and resource (write a run of posts), plus scope qualifiers that matter: ONE social group, AI Planner, caption per platform, theme, image scene. That clearly separates it from single-post siblings like create_post and from the plan-editing siblings it names.

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?

Gives explicit preconditions (tell the user how many posts and ask first, because credits are consumed), an explicit non-action (do not re-call after a timeout), the alternative to use instead (list_plan_posts), and the follow-up tools to offer afterwards. Essentially a complete when/how-to decision tree.

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