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

Beyond the annotations (which already flag non-read-only, non-destructive, non-idempotent), it discloses that 'nothing is traded by this call,' that a new follow supersedes the existing one, what the runner does (mirrors fills under the record), and that it can be stopped with unfollow. This is rich operational context the structured fields do not carry.

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 dense, front-loaded prose that puts the core action and plan scope first, then the record contents, then the return values. Every clause carries information, though the single long paragraph is slightly heavy and could be broken up for scanning.

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 no output schema, the description carries the return burden and does so well: the record, its digest (the coordination record follow.created), and the attribution prefix copy:<you>:<model>. Combined with the supersede and runner behavior, an agent has everything needed to call and interpret the result.

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 baseline is 3, but the description adds genuine meaning: sizing as either fixed_notional usd or proportional bps of balance, the specific cap fields, and that follower_wallet is the address the runner signs mirrors with. It reinforces and interprets the schema rather than merely restating it.

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 opens with a concrete verb and resource: 'Follow a trading model (max plan): creates the follow record.' It explicitly separates itself from the siblings it could be confused with — follow_quote (validation), unfollow (stopping), and models (attribution source). An agent can distinguish it 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?

It states the key constraint ('one active follow per model, a new one supersedes it'), points at follow_quote as the validation reference, and names unfollow as the way to stop. The main gap is that it doesn't spell out the precondition for calling it versus first quoting, leaving the order of operations partly implicit.

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