create_baton

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

With no annotations, the description carries the full behavioral burden and succeeds: it discloses that creation is billable and charged once, that payment comes from rs_live_* balance, the 3MB content limit, the 422 error path, and that hash-chained batons must be created empty. This is far beyond minimal disclosure.

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?

The description is long, but the tool is complex and every sentence adds a decision-relevant fact: preset definitions, billing, content rules, the hash-chaining constraint, and examples. Critical constraints are front-loaded before the examples.

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?

It is remarkably complete for a creation tool: presets, cost, key funding, constraints, error handling, and follow-up writes are all covered. The main gap is that no output schema exists and the description never states what the create call returns (e.g., a baton identifier/address), which an agent would need to chain read_baton or append_to_baton.

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 only 10%, so the description compensates by explaining the meaning of preset values, content size/encoding constraints, flags.hashChaining, and the role of customShape. It does not spell out every auxiliary parameter (name, tags, contentType, contentEncoding, customShape sub-fields), but the decision-critical parameters are well covered.

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 specific verb and resource ('Create a baton — a prepaid storage object') and then defines each preset by its intended behavior (store, share, append log, snapshot, tamper-evident log). This clearly distinguishes creation from the sibling read_baton/append_to_baton tools.

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 explicitly tells the agent to quote the shape first with quote_baton, to pass content inline or defer to append_to_baton, and provides two concrete call examples. It even states the invalid case (hash-chained content returns 422), so the agent knows when not to include content.

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