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

With destructiveHint=true and idempotentHint=false already declared, the description adds the details those flags cannot convey: no double-posting for unknown outcomes, content unchanged so existing approvals hold, monthly limits still apply, public immediate publish, and unavailability in an unclaimed sandbox. No claim conflicts with 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?

Front-loaded with the action and the core constraint, and every sentence contributes new information (fix-first, never-retried cases, approval retention, consent gate). It is dense and somewhat long for a single paragraph, but there is little true waste.

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 2-parameter mutation with a safety-relevant annotation set and no output schema, the description covers preconditions, exclusions, side effects, licensing/plan limits, and sandbox availability — everything an agent needs to decide whether and how to invoke it.

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?

Only workspace_id carries a schema description (50% coverage); post_id is undocumented in the schema, and the description never explains it beyond the narrative reference to 'a post.' With half the parameters undescribed, the description does not compensate for the gap, so baseline 3 applies.

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 (sends again / retry) on a specific resource (a post's failed accounts) and immediately bounds the scope: 'to the accounts it failed on; accounts it already reached are left alone.' That scope clause distinguishes it from the generic scheduling/publishing siblings.

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 precondition ('Fix the cause first'), points to the sibling that supplies the error detail ('get_post shows each account's error'), enumerates cases that will not succeed (disconnected/paused accounts, unknown-outcome accounts), and sets a consent gate ('retry only when your human wants it'). Both when-to-use and when-not are covered.

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