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

Annotations already declare non-read-only, non-destructive, non-open-world. The description adds valuable context beyond that: the operation saves a draft rather than publishing, grounds output in the workspace Brain unless brain_id overrides, and consumes one AI generation. These side-effect and cost disclosures are useful for an agent, though error handling and draft lifecycle details are absent.

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 core action and scoped detail in two sentences. The parentheticals add useful context but could be trimmed slightly; overall it is efficient and every sentence contributes something material.

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?

Given a 3-parameter write tool with no output schema and rich annotations, the description covers the essential job, the draft-only side effect, the Brain grounding rule, and AI cost. It leaves the return value (e.g., draft identifier) unstated, but that is a minor omission given the lack of an output schema.

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 0%, so the description carries the burden. It explains brain_id semantics well (defaults to the workspace's Brain unless another is named) and gives the platform parameter meaning with examples. It does not restate the full enum, mention the default 'x', or describe the idea parameter beyond 'from an idea', leaving some gaps.

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 ('Write one social media post'), names the resource and platform scope, and explicitly distinguishes itself from publishing tools by stating the post is saved as a draft and nothing is published. An agent can distinguish this from publish_now and schedule_post without opening any 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?

Clear context: use this to generate a single draft post grounded in the Brain, and it will not publish. It implies when not to use it (anything requiring publication), but stops short of explicitly naming alternatives like publish_now or schedule_post. No prerequisites or exclusions are stated beyond the draft-only nature.

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