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

The readOnlyHint annotation already establishes safety, but the description adds meaningful behavioral context: it is a free/guided help call, scoped to tools 'visible on this MCP facade,' and it returns specific categories including 'what it refuses' and the interaction contract. This goes well beyond the annotation, though it stops short of detailing error-handling or rate-limit behavior.

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 sentences deliver high information density: the first defines scope and enumerates outputs, the second gives the actionable call pattern. No filler or redundancy; every phrase 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?

Despite having no output schema, the description compensates richly by listing the major output dimensions (when-to-use, refusals, example, limits, outputs, provenance, next calls, interaction contract). For a help/metadata tool, this is comprehensive and leaves little ambiguity about what the caller will receive.

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?

The schema already documents tool_name as 'Exact tool name from tools/list' (100% coverage), so the baseline is 3. The description adds value by reinforcing that the tool targets one tool on the facade and by instructing the agent to first use tools/list, which effectively explains how to populate the parameter correctly.

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 clearly identifies the tool as providing 'free blind-caller guidance for one tool visible on this MCP facade' and enumerates exactly what it returns (usage, refusals, example, access limits, outputs, provenance, next calls, interaction contract). This distinguishes it from the sibling data-retrieval tools (get_catalog, get_fx_rates, get_pack), which are content-focused rather than meta-help tools.

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?

Gives explicit workflow guidance: 'Use tools/list to discover names, then call this before an unfamiliar tool.' This tells the agent when to invoke it and what precedes it, making the intended context of use unambiguous.

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