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

Annotations cover the safety profile (not read-only, not idempotent, open world), and the description adds real behavioral context beyond them: draft creation vs. scheduling an existing draft, Substack-only paywall/subscribe markup behavior, and the LinkedIn session-sync fallback that silently saves as a draft. It does not discuss retry/rate semantics, hence not 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?

Purpose and primary mode selection are front-loaded, and each sentence carries distinct information (draft creation, media/paywall rules, LinkedIn caveat, return advisories). It is dense but not padded; a slightly tighter grouping of the Substack paywall sentences would earn a 5.

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 23-parameter multi-destination tool, the description covers the cross-cutting behaviors an agent needs (draft-vs-schedule branch, destination constraints, degradation paths) and an output schema handles return values. It omits guidance on which sibling to use for amending or cancelling already-scheduled items, leaving a small gap.

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 96%, so the schema already documents nearly every parameter in depth; the baseline is 3. The description's parameter-level statements (media/video requires Substack as sole platform, paywall markers create native paywalls, audience/email governed by supplied fields) largely restate schema text rather than adding new interpretation.

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?

Opens with a specific verb+resource+destination scope ('Schedule an article to Substack, Medium, LinkedIn Articles, or X') and immediately states the draft-creation behavior. An agent can distinguish it from schedule_note, create_draft, and reschedule_scheduled_item without opening the 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?

Gives clear situational context: draftId absent means a new draft is created, LinkedIn Articles needs a separate browser-session connection, and a pending session sync degrades to draft-without-scheduling. It does not name sibling alternatives (e.g. amend_scheduled_item, reschedule_scheduled_item) for when-not scenarios, so it stops short of a 5.

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