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

Beyond the annotations, the description discloses the most consequential behavior: a draft without `preview` is a dry run that returns what the draft would yield over a day, the matched pieces, and a `confirm` digest — a preview/commit two-phase flow that no annotation implies. 'The same move again changes nothing' reinforces idempotentHint=true. It stops short of stating permissions or error conditions, but this is substantive added context.

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?

It is compact — three sentences — but not front-loaded: the opening clause is figurative rather than declarative, and the middle sentence chains four ideas ('a day, the pieces it finds, and a `confirm` digest') in a way that slows parsing. Nothing is redundant, but the wording costs more than it earns in places.

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?

An output schema exists, so return values needn't be described, and the preview/commit mechanics are covered. Still, for a 7-parameter tool where two parameters and most of the `draft` structure are undocumented in prose, an agent gets an incomplete picture of valid inputs and of what happens when neither target nor draft fits.

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?

At 43% schema coverage the description carries weight, and it does explain `target` forms, the amplitude ladder (away/low/normal/high) as 'a step', and the `preview` digest as the confirm token. However `note` and `language` go unmentioned and the `draft` sub-fields are left entirely to the schema, so the compensation is only partial.

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 does convey two distinct operations — moving an existing 'magnet' via target+amplitude, and saving a draft definition — but it does so in heavily metaphorical prose ('Move one of the reader's magnets, what draws their own edition'). The plain verb+resource ('save an interest/magnet to the reader's profile') is never stated, so the agent must decode the metaphor before it can confirm the tool's job.

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 gives real branch logic: use the target+amplitude path for a named subject, and the draft path 'For a subject no target names'. It also spells out the preview-then-confirm sequence. But it never differentiates from siblings like my_interests or why, and gives no prerequisites or when-not-to-use guidance.

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