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

Without annotations, the description carries the burden, and it delivers useful behavioral context: the decision is tamper-evident, anchored, and appended to a record trajectory checkable against DA's external entry. It also surfaces default EE/preset cost behavior and points to a pricing endpoint, though it does not deeply cover all side effects such as error handling or exactly what the response returns.

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 for a 24-parameter tool and front-loads the key decision trigger. Slight redundancy exists around 'record' and 'decision', but no sentence seems wasted; the pricing and default discussion earn their place by explaining aggregation of many parameters.

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?

For a complex creation endpoint with 24 parameters, the description gives enough shared context: scope, timing, sibling distinction, and EE/pricing defaults. It does not describe the output shape, which is likely significant because no output schema is present, but the description nevertheless sets up an agent well for correct invocation.

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 high, so the baseline is 3; the description adds extra value by explaining how the four EE axes interact as a preset, what 'omitting EE axes' means in practice, and that EE_standard costs 45 DAC while EE_basic costs 10 DAC. This helps an agent understand the decision-relevant implications of parameters without opening the pricing endpoint.

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 uses a concrete trigger ('an action crosses an external boundary: payment, delegation, or agreement') and a clear primary action ('Record a tamper-evident decision'). It also distinguishes itself from the sibling propose_bilateral by stating that this route is for self-declared decisions while counterparty declarations belong to the other endpoint.

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 explicitly states when to use this tool and when not to: use it for self-declared decisions, and use propose_bilateral when a counterparty is involved. It even gives timing guidance ('before you execute, or after a decision you have already made'), so an agent gets clear contextual boundaries.

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