finance_stripe_xero_writeback_fanout

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

Annotations already declare destructiveHint=true, idempotentHint=false, openWorldHint=true, and readOnlyHint=false, so the agent already knows this is a non-idempotent, potentially destructive call. The description adds only the execution-context detail that it routes through the platform dispatcher under JWT/tenant/company scope, which is useful but does not explain what the destructive effects are or what resources (Stripe, Xero, accounting records) get modified.

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 short, front-loaded with the core instruction, and has a clean `Args` block. Every sentence earns its place; the writing is not padded. It could have been expanded, but conciseness itself is handled well.

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?

Given the presence of an output schema, return values are covered, but the actual domain behavior is not. With a destructive finance tool that fans out writebacks between Stripe and Xero, an agent needs to know what business operation is being requested, what data is affected, and how it differs from dozens of other `finance_*` and `stripe_*`/`xero_*` sibling tools. None of this is conveyed, so the definition is incomplete for correct invocation decisions.

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?

While the input schema gives only property names and defaults, the description adds rough intent: `message` is a free-text objective and `inputs` is an optional JSON string. This is basic compensation for the 0% schema-description coverage, but it leaves the format and valid content of `inputs` unspecified, so an agent still cannot know the exact structured payload shape.

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 opening sentence, 'Run the finance domain agent action stripe_xero_writeback_fanout', largely restates the tool's name and labels it as a domain agent action without describing the underlying business effect. The only additional behavioral note, 'Routes through the platform's domain-agent dispatcher', describes routing mechanics, not what the action accomplishes, so an agent is left guessing about what 'writeback_fanout' means.

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?

The description provides no explicit when-to-use or when-not-to-use guidance, and it does not compare itself to any alternatives such as `dispatch_domain_agent` or the many direct Stripe/Xero or finance_* tools. When to select this tool must be inferred entirely from the action name in the tool title.

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