legal_tax_obligation_scan

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

Annotations already establish the safety profile (destructiveHint=true, readOnlyHint=false, idempotentHint=false), so the bar for the description is lower. The description adds genuine context beyond annotations: the tool is a forwarding wrapper that routes through a domain-agent dispatcher under JWT, tenant, and company scope, which clarifies auth requirements and execution semantics. It does not, however, elaborate on what destructive side effects the underlying action may have, leaving that fully to the annotations.

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 compact and front-loaded: the core statement about running the legal domain action appears first, followed by routing context and a cleanly formatted Args list. Every element earns its place, though the Args block partially duplicates schema property names without much extra detail beyond semantics.

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 no explanation, and annotations cover the destructive profile. The description covers dispatch routing, scoping, and both parameters, which is adequate for invocation. The notable gap is functional context: an agent still cannot tell what a tax obligation scan produces, what objective text should contain, or why this tool is preferable to its GRC counterpart, so completeness for a dispatch-style tool is only partially satisfied.

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 carries the full burden for parameters. It compensates well: message is documented as the free-text objective and inputs as an optional JSON string of structured inputs, giving an agent a clear sense of how to populate each. It stops short of providing examples of valid 'inputs' structure, but for only two simple parameters this is solid semantic coverage.

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 states the verb ('Run') and resource ('tax_obligation_scan'), and identifies it as a legal-domain agent action, which loosely separates it from grc_tax_obligation_scan. However, it never explains what a tax obligation scan actually does or accomplishes — the functional purpose is left entirely to inference from the name, so the description borders on restating the tool's title rather than defining its behavior.

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 closely related siblings such as grc_tax_obligation_scan, legal_tax_compliance_report, legal_tax_deadline_alerts, or dispatch_domain_agent. The 'Routes through the platform's domain-agent dispatcher' line explains the execution mechanism but gives no selection criteria, exclusions, or conditions for choosing an alternative.

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