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

Annotations already say readOnlyHint=true/destructiveHint=false, and the description reinforces rather than contradicts that ('SAVES NOTHING AND POSTS NOTHING'). It then adds behavior annotations can't express: it is stateless and requires the caller to pass back usedShapes, it returns up to three targeted questions instead of a draft when material is missing, and it refuses to fabricate years, numbers, names or events.

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 purpose and the not-a-publisher warning, then the shape rotation, then the missing-material protocol. Dense but every block carries operational information; there is minor redundancy between 'leaning on what their best posts did' and 'The first draft is in the way of their best posts', which repeats the same idea.

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?

No output schema exists, and the description compensates fully by specifying both possible return shapes (a draft, or up to three questions with example answers) and the loop that follows each. It also covers statefulness, language defaulting, and the terminal publish step, so an agent can drive the whole interaction without guessing.

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 already 100%, so the schema documents each parameter's format. The description still earns extra credit by explaining the usedShapes rotation contract and by mapping the opaque enum values (their_own_way, story_lesson_advice_you, low_to_high, timeline, starting_line) to human-readable shapes, plus clarifying that 'details' should carry the user's answers to prior questions.

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 — 'drafts ONE LinkedIn post in the user's own voice' — and immediately differentiates itself from create_post by declaring it saves and posts nothing. The voice-mimicry mechanism (reads their recent posts, leans on best-performing shapes) makes the resource unambiguous even among 200+ siblings.

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?

Explicit positive guidance ('Use this instead of writing a post yourself'), explicit negative guidance ('For small edits the user asks for, change the draft yourself — calling again moves to the next shape'), and explicit handoff to a sibling ('publish it with create_post only after the user says yes'). The follow-up-call protocol and the writeAnyway escape hatch are both defined.

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