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

The annotations (`readOnlyHint: true`, `idempotentHint: true`, `destructiveHint: false`) already establish that this is a safe, read-only check. The description adds value by detailing the specific response codes (ALLOW, HOLD, BLOCK) and their operational meanings, which the annotations do not cover. No contradiction exists.

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 extremely concise at four sentences, with the core purpose stated in the first sentence. Every sentence adds critical information: purpose, return values, and usage guidance. There is no wasted text, and the structure is front-loaded with the most important 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?

Given the tool's high complexity (9 parameters, no output schema), the description effectively explains the workflow context and expected outcomes. It lacks details about what happens on errors or timeouts, which would be useful for a blocking tool. However, the annotations declare readOnlyHint and idempotentHint, which mitigate this concern. The description is complete enough for an agent to use correctly in the intended workflow.

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 all 9 parameters are documented in the schema itself. The description does not repeat parameter details but adds minimal context above the schema. Given high coverage, a baseline of 3 is appropriate; the score is raised to 4 because the description adds workflow context (e.g., 'if acting under a delegation' for `delegation_id`) that aids understanding beyond the bare 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 uses specific verbs ('Check', 'Returns') and identifies a clear resource ('proposed payment against the agent's active policy'). It distinguishes itself from sibling tools like `settle` and `policy.create` by explicitly stating 'Run this before every settlement call', making its role in the workflow unambiguous.

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 provides explicit guidance on when to use the tool ('Run this before every settlement call') and interprets all possible return values with actionable directives ('ALLOW = proceed. HOLD = route to human review queue. BLOCK = halt, do not proceed'). It implicitly distinguishes from siblings like `policy.create` by focusing on checking an existing policy rather than creating one.

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