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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower. The description adds genuine behavioral context beyond them: the compute:auto/server/browser delegation semantics, browser delegation URL returns for gpu:true nodes, transient non-retention of inputs, and the exported AP2 execution_hash for provenance. It does not disclose rate limits or failure modes.

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?

Purpose is front-loaded, but the definition is padded with family boilerplate, a documentation URL, and a long FV-status receipt hash that mostly serves provenance rather than tool selection. It is readable but not lean.

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 not be explained, and annotations carry the safety profile. The description covers compute modes, provenance chaining, upstream dependency and the artifact export, which is enough for an agent to invoke it correctly; only the policy_parameters contract remains thin.

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 100%, so the schema fully documents compute, parent_hashes, parent_tool_ids and policy_parameters. The description largely restates the compute-mode semantics already in the schema and adds no field-level meaning (e.g. what policy_parameters fields the cover-2 kernel expects), so baseline 3 is appropriate.

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 opening clause names a specific verb+resource ('CCP Default Fund Cover-2 Sizing') and identifies it as a risk_parameter compute node, which distinguishes it from the related sibling recompute_ccp_default_waterfall. However, the purpose is buried behind boilerplate framing that is shared across the whole tool family, so the actual computation performed is not described.

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?

It names the upstream artifact consumer (qfa-03-stress-test-engine) and instructs the use of synthetic/anonymised inputs, which is useful routing context. But it never says when to choose this over alternatives such as recompute_ccp_default_waterfall, nor states preconditions for the parent_hashes chain.

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