evaluate_tool_approval

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly reveals that allowlisting is not a grant, that host-injected fields are merged into the hash and cannot be overridden, and that ambiguity (wildcards, missing resource, unparseable arguments) results in denial. These are security-critical behaviors that an agent must know before invoking.

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?

Three tightly packed sentences with zero fluff. The first sentence states the purpose, the second clarifies a key nuance (allowlist vs grant), and the third specifies the ambiguity-denial rule. Information density is high and every sentence earns its 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?

For a tool with nested objects and a nuanced policy, the description covers the critical decision logic well (allowlist behavior, host-bound merging, ambiguity handling). However, it does not enumerate the full set of possible outcomes beyond RECEIPT_REQUIRED and 'deny on ambiguity' — it never states what an approval result looks like, nor what happens for non-allowlisted tools. This leaves a minor gap in the agent's understanding of return values, which is notable given there is no output schema.

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?

Although the schema fully describes the 'call' and 'policy' objects, the description adds substantial meaning beyond the schema: it explains how host_bound and _meta.cubiczan.host_bound are merged, that arguments are hashed with host-injected fields, and that wildcards/missing resources/unparseable args trigger denial. This semantic layer is essential for correct invocation and is not present in the raw 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 states a clear, specific action: 'Evaluate a proposed MCP tool call.' It further clarifies the tool's role by contrasting a managed allowlist with a grant, and by detailing the ambiguity-denial behavior. This distinctively separates it from sibling tools like authorize_tool_call (which likely grants) and evaluate_spend_gate (which likely focuses on spend policy).

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 implies this is the pre-approval evaluation step by noting that allowlisted tools still return RECEIPT_REQUIRED and that ambiguity denies. However, it does not explicitly name alternative tools or provide when-to-use/when-not-to-use guidance. It leaves some inference to the agent about choosing this over sibling evaluation tools.

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