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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, but the description adds material behavior: nothing is scheduled, approval or change requests flow back through the conversation, and article scheduling is restricted to personal accounts. That is context an agent cannot derive from the annotations alone.

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 the 'no scheduling' guarantee are front-loaded in the first two sentences, and every later sentence carries a rule. The middle sentence is a long comma-separated list that is dense to parse, which keeps this short of 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?

With a rich nested input schema, an output schema, and full annotation coverage, the description supplies the workflow, the approval gate, and the account/SEO constraints an agent needs. The remaining detail about return payloads lives in the output schema, so nothing critical is missing, though the per-platform edge cases are left to the schema text.

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?

Top-level schema coverage is 0%, but the description compensates with construction rules for the calls payload: full inline content rather than draftId, explicit dates with UTC offsets, time zones, explicit account identifiers rather than implicit multi-account defaults, subscriber-email/audience/SEO choices for articles, and clientRequestId on each note. It also explains where the voice object's value comes from.

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?

The description states a precise verb+resource: it shows the exact schedule_note and schedule_article calls for review, and immediately declares 'No scheduling occurs.' This cleanly separates it from the schedule_note/schedule_article siblings that actually execute.

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?

It says when to use it (before scheduling, for writer review), when to route elsewhere ('For unsupported advanced options, review in the conversation instead'), names the prerequisite tool for voice ('Voice selection comes from open_publishing_studio'), and states the sequencing rule: execute scheduling only after the panel returns approval.

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