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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description aligns with these and adds valuable context: that results are not guaranteed through execution ('Execution rechecks everything'), implying preflight results may become stale. No contradiction with annotations.

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?

Two efficient sentences. The first front-loads the core function and its exclusions; the second adds a critical caveat about result validity. Zero wasted words.

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 5 unannotated parameters, a nested 'input' object, and no output schema, this description is inadequate. An agent cannot determine what to pass in 'input', what 'operation' or 'capability' mean, or what a response looks like. The high-level purpose is clear but operational detail is missing.

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% across 5 parameters (input, intent, operation, capability, idempotency_key). The description mentions 'validation, scope and remaining capability budget' as high-level concepts but never maps them to parameters or explains what values are expected. With zero schema coverage, the description was expected to compensate but doesn't.

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 a specific verb ('Inspect') with clear resources (validation, scope, capability budget) and explicitly states what it does NOT do (reserving, billing, executing). This differentiates it from siblings like xguard_execute and xguard_quote without ambiguity.

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 'without reserving, billing or executing' clause makes the when-to-use clear: for side-effect-free inspection. 'Execution rechecks everything' implies execution is a separate step, but the description doesn't explicitly name the alternative tool (xguard_execute) or state exclusion conditions as directly as it could.

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