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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description nonetheless adds genuinely useful context the annotations cannot carry: the same validation checks as a new publish (subscription, daily limit, connection health, caption limits), that the old error is cleared, and that no monthly upload credit is consumed. It stops short of describing what a failed retry returns or how errors surface, which keeps it from a 5.

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 Retry-button analogy, then preconditions and alternatives. Four sentences is slightly long and the credit-saving detail could be trimmed, but each sentence carries actionable content rather than 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?

For a mutation tool with no output schema and three well-documented parameters, the description covers the decision path (how to find failures), the preconditions (reconnect, fix caption), the side effects (checks re-run, error cleared, re-queued) and the cost model (no upload credit). An agent has everything needed to call this correctly.

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 all three parameters including the ISO 8601 future/one-year constraint and the idempotency window. The description only adds the behavioral nuance that scheduled_for re-queues rather than publishing immediately, and it never mentions idempotency_key. Baseline 3 applies when 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?

States a specific verb and resource ('Publishes a failed post again'), and pins down the exact scope (only failed posts) plus the mental model of the ShortSync Retry button. This distinguishes it cleanly from publish_now and schedule_post, which operate on new posts.

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 routes the agent: use list_scheduled_posts (status: 'failed') or get_workspace_status to find candidates, and use update_post/batch_update_posts instead when the failure was a caption-length problem since those re-queue on their own. It also states the prerequisite of the user reconnecting a disconnected account first.

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