finance_aging

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

The annotations already mark this as destructive, non-read-only, non-idempotent, and open-world. The description adds some useful scoping context by mentioning JWT, tenant, and company scope, but it does not disclose what side effects the action may have or warn that it can be destructive. It does not contradict the annotations, but the behavioral transparency burden is only partially met.

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, and organized into a clear action sentence followed by an args list. It avoids unnecessary padding and is easy to scan. The main weakness is lack of substantive content, not structural bloat.

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 generic dispatcher nature and 0% schema coverage, the description should explain what finance_aging does, when to invoke it, and what inputs are expected. It only provides routing/scoping context and vague parameter labels. An agent selecting among the hundreds of siblings would still be unsure whether finance_aging is the right tool for an aging report, a finance workflow, or something else.

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 carry parameter meaning. It does provide basic semantics: message is a 'free-text objective' and inputs is an 'optional JSON string of structured inputs.' However, it does not explain what structured inputs finance_aging accepts, what a valid objective looks like, or how the two parameters interact. This is a minimum viable explanation but not sufficient for correct structured invocation.

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 only says 'Run the finance domain agent action finance_aging,' which restates the tool name without explaining what the action actually does or what outcome it produces. Routing/dispatcher details do not clarify whether this computes an aging report, mutates data, or returns a financial summary. It fails to distinguish finance_aging from the many other finance_* sibling 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?

No explicit guidance is given for when to use this tool versus alternatives like finance_chat, finance_query_data, or dispatch_domain_agent. The description simply states that it routes through the domain-agent dispatcher, which is a mechanism, not a selection criterion. An agent cannot determine which user request should map to this tool.

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