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

With no annotations, the description carries the full behavioral burden. It usefully discloses a cost (0.002 USDC), which is a real trait, but says nothing about what the inspection detects, whether it blocks installation, what happens on a failing manifest, or any auth requirements. The safety profile is essentially unspecified.

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?

A single front-loaded sentence plus a price tag; no filler. It may be too terse for a nested-object tool, but it wastes nothing.

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 tool takes nested objects, has zero schema description coverage, and no annotations, yet the description omits the policy parameter, the detection semantics, and the meaning of a pass/fail result. An output schema exists so return values needn't be explained, but the gaps in scope and parameters leave it inadequate.

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 0% with two nested-object parameters, so the description must compensate and does not. The required 'manifest' object is somewhat inferable, but the optional 'policy' object is completely opaque in both schema and description.

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?

States a specific verb (Inspect) and resource (MCP manifest) with a clear timing qualifier (before installation or trust). It distinguishes itself reasonably from siblings like tool_output_firewall, though the exact scope of 'inspect' is left fuzzy.

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 phrase 'before installation or trust' gives an implied trigger condition, so an agent knows roughly when to reach for it. However, it names no alternatives and offers no exclusions, which is weak given the many adjacent preflight/guard siblings (preflight, tool_call_policy_guard, counterparty_risk_preflight).

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