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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful traits beyond that: 'fail closed', 'deterministic', 'evidence-bounded' and 'signed'. These are valuable but delivered as unconnected fragments rather than coherent behavioral context.

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 text is short but badly malformed: a dangling semicolon, an orphaned pricing fragment '0.003 USDC', and a trailing attribute list with no connective tissue. The fail-closed condition is front-loaded, but the fragments do not earn their place.

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 and annotations cover safety, so return values need not be described. Still, for a policy guard surrounded by near-identical siblings, the description never explains what it does, when to invoke it, or how it differs from agent_budget_guard or mandate_reserve, leaving the agent unable to route correctly.

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 zero declared parameters and 100% schema description coverage, the baseline is high. The description's references to 'delegated authority', 'per-call limit' and 'remaining budget' map onto the schema example fields (mandate.active, max_per_transaction_atomic, remaining_atomic), adding mild semantic anchoring for a free-form schema.

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 conveys the domain (delegated authority, per-call limit, remaining budget) and a fail-closed behavior, so an agent can guess this is a spend-policy guard. However, it never states a clear verb or what the tool actually evaluates or returns, and it is confounded by stray fragments like '0.003 USDC'. Purpose is implied rather than stated.

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 when-to-use guidance and no routing to alternatives, despite many closely related siblings (agent_budget_guard, mandate_reserve, payment_capability_preflight). The only implied condition is that it fails closed on insufficient authority, which is a behavior, not a selection guideline.

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