finance_stripe_orchestrator

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

Annotations already indicate this is destructive (destructiveHint: true), non-idempotent, and not read-only, so the description's job is to add behavioral context. It mentions routing under the agent's JWT, tenant, and company scope, which is useful, but it does not disclose what side effects may occur, what gets changed, whether approvals are required, or what the output schema contains. The description is neutral and does not contradict annotations, but it carries insufficient behavioral weight for a destructive tool.

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 and front-loaded with the core instruction. The Args section is compact and adds two useful one-line meanings. It is bigger than needed for a two-parameter tool, but every line serves a purpose, so conciseness is acceptable.

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 an output schema exists and the parameter count is only two, the description still leaves major gaps: it never explains what the orchestrator does, what a valid message/inputs combination looks like, what side effects to expect from a destructive call, or when to prefer a more specific finance_stripe_* sibling. For a destructive generic dispatcher, this is not enough.

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%, so the description must compensate for the bare schema, and it does only minimally. It labels message as 'Free-text objective for the action' and inputs as 'Optional JSON string of structured inputs', which is slightly more than the schema's default values, but it omits any example, expected shape of the JSON, or relationship between message and inputs.

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 says it 'Run[s] the finance domain agent action' named finance_stripe_orchestrator, which identifies the verb and resource but is nearly a tautology since the tool name already says the same thing. It adds that it routes through a domain-agent dispatcher, but does not explain what the Stripe orchestrator actually does (e.g., reconcile, audit, recover failed payments), so an agent cannot tell it apart from the many other finance_stripe_* siblings.

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?

There is no guidance on when to use this tool versus the many sibling finance_stripe_* tools such as finance_stripe_ledger_reconciliation, finance_stripe_revenue_audit, or finance_stripe_subscription_health. The phrase 'Run the finance domain agent action' implies it is a generic gateway, but it never states when an agent should pick this over a more specific sibling or the closely named dispatch_domain_agent tool.

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