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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds context about the deterministic nature and internal components (chi statistics, energy distribution, gradient patterns, phase coherence), going beyond the annotations without contradiction.

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 paragraphs front-load the core purpose and key details. Every sentence contributes value, but some redundancy exists (e.g., listing data types twice). Could be slightly tighter.

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 without an output schema, the description adequately explains the return format (labeled vector with dimension details) and works across diverse inputs. Use cases and data variety are covered, making it complete for most agent scenarios.

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 covers all parameters with descriptions (100% coverage). The description adds meaning by explaining the difference between field_level values (0 vs 1) and encoder_type options (auto-detect), though the schema already includes these details.

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?

Clearly states it produces a physics embedding (fingerprint) of any data item, with specific dimensionality at different levels. Use cases (similarity search, clustering, drift detection) are explicitly mentioned, distinguishing it from sibling tools that focus on action surfaces, risk, comparisons, etc.

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?

Describes broad applicability to structured data but lacks explicit guidance on when to use versus alternatives like waveguard_compare or waveguard_scan. No when-not-to-use or prerequisite information is provided.

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