djd-agent-score-mcp

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

Annotations indicate this is not read-only (readOnlyHint: false) and interacts with external systems (openWorldHint: true). The description adds critical behavioral context not present in annotations: the $0.25 USD payment requirement via x402, and the specific return structure (score, tier, confidence, etc.) despite the absence of a formal output schema.

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?

Efficiently organized with clear visual hierarchy: purpose statement, usage trigger, cost warning, and return documentation. Every line serves a distinct function—no filler text. The front-loading of the core action ('Force a re-score') followed by conditions and constraints is optimal for agent parsing.

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 complexity (paid endpoint, on-chain dependency) and lack of output schema, the description compensates perfectly by documenting the exact return object structure. Combined with complete schema coverage for inputs and explicit cost disclosure, the description provides sufficient context for correct invocation and response handling.

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?

With 100% schema description coverage, the baseline is appropriately 3. The description lists the wallet parameter but essentially mirrors the schema's pattern specification ('0x + 40 hex chars' vs schema's regex pattern). It adds no additional semantic context (e.g., no examples of valid/invalid addresses or usage notes) beyond what the structured schema already provides.

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 opens with a specific verb-noun combination ('Force a re-score of an AI agent wallet') that precisely defines the operation. It distinguishes from siblings like 'score_basic' and 'score_full' by emphasizing the 'refresh' aspect—using 'latest on-chain data' and targeting 'cached' scores—making the unique value proposition clear.

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?

Provides explicit temporal triggers ('when you suspect the cached score is stale', 'after known on-chain activity') that clearly indicate when to invoke this tool versus simply reading existing scores. The guidance implicitly defines when NOT to use it (avoid unnecessary paid calls when data is fresh).

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