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

Annotations already declare destructiveHint=true, openWorldHint=true, and non-idempotency, so the bar is lower. The description adds real value beyond them: retries are safe only if you reuse the identical Idempotency-Key and settings, earlier receipts are preserved, and the story must be unchanged. The retry guidance is complementary to idempotentHint=false rather than contradictory, since the key is what supplies idempotency.

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?

Three dense sentences, front-loaded with the action and scope, with the retry instruction and the read-tool pointer following. Every clause carries information; nothing is padded. It is terse to the point of being slightly telegraphic, which costs a little on readability.

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 mutating, open-world tool with six parameters, nested objects, and no output schema, the description covers the essential caveats: story must be unchanged, only unreached destinations, receipts preserved, retry via key. It leaves unaddressed whether facebookTarget/tiktokSettings become required per selected platform, but that is the schema's domain rather than a missing behavioral disclosure.

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 50%: platforms, scheduledFor, facebookTarget and Idempotency-Key are documented in the schema, while storyId (pattern only) and tiktokSettings are not. The description echoes 'destinations', 'time', 'settings', and the key but supplies no format detail for the undocumented parameters. Baseline 3 is appropriate given partial coverage.

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 concrete verb+resource (schedule a saved story) with two sharp scoping qualifiers: 'unchanged' and 'destinations it has not reached'. These distinguish it from publishStory (immediate send) and bulkSchedule (many items), even though no sibling is named outright. The core action an agent must identify is unambiguous.

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 two actionable directives: confirm destinations and time, and consult getStory/getCalendar for delivery jobs. It also covers the retry path with the Idempotency-Key. However, it never states when to prefer this over publishStory, schedulePost, or bulkSchedule, which is the primary routing decision among these siblings, so usage is implied rather than established.

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