Private allocation decision card

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

The description adds substantial behavioral context beyond the readOnlyHint, openWorldHint, and idempotentHint annotations. It discloses default state ('Default DRAFT'), caller assertion semantics ('USER_SELECTED is a caller assertion, never a transaction or recommendation'), and persistence behavior ('No disk writes; save privately with the local save-card command. Never publish cards.'). There is no contradiction with 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 four tightly written sentences with no filler. It front-loads the core purpose, then states the essential usage caveats and persistence rules. Every sentence carries meaningful, non-redundant information.

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?

The description covers status defaults, caller assertion semantics, disk-write behavior, and the save-card alternative, which is strong contextual coverage especially given the annotations and output schema. The main gap is the undocumented meaning of the required allocation object, which relies on the schema's structural names. Overall, an agent can likely select and invoke the tool correctly in most cases.

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?

With 0% schema description coverage, the description must compensate, but it only addresses selectedScenario and reason. The required allocation parameter, including its nested pools, tokenIds, scenarios, and weightsBps, receives no semantic explanation in the description. The schema provides structure but not the meaning needed to construct a valid allocation.

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 a specific verb and resource: 'Return an exportable decision card with allocation evidence, sensitivity and content checksum.' It clearly identifies the tool's output and purpose. It does not explicitly contrast with sibling tools, but the decision-card deliverable is distinct enough to be recognizable.

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 gives explicit conditions on when to set fields: 'Set selectedScenario and reason only when explicitly chosen by the user.' It also provides guidance on what not to do and an alternative action: 'No disk writes; save privately with the local save-card command. Never publish cards.' It does not name sibling tools as alternatives, but it offers clear context and exclusions.

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