Arsenkin: prepare

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

Annotations already mark this as a non-read-only write (readOnlyHint=false) with destructiveHint=false, and the description adds materially: the write is limited to an 'approval record only' and incurs 'no spend'. That clarifies the blast radius in a way the annotations alone do not, though it says nothing about reversibility or the non-idempotent behavior the annotation flags.

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?

Three short clauses, front-loaded with purpose, then precondition, then write scope. No filler and every sentence earns its place.

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 need not be described, and annotations cover the safety profile. However, the tool's core input — the payload that defines the job being approved — is completely opaque in both schema and description, leaving the agent unable to construct a correct call.

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% for both required parameters, and the description adds no meaning for 'profile' or the nested 'payload' object beyond the vague notion of a 'job'. With the payload schema wide open (additionalProperties: true, no defined properties), this is the tool's critical gap and the description does not compensate.

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 ('Create a bounded approval for one paid job') and implicitly differentiates from the batch sibling by scoping to a single job. An agent can tell this apart from arsenkin_batch_prepare and arsenkin_estimate without opening a 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?

Gives an explicit sequencing precondition ('Use after the user saw the estimate') and names the follow-up tool ('then arsenkin_submit'). It stops short of naming the alternative to use instead when multiple jobs are involved (batch_prepare), but the trigger context is clear.

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