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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it warns about spoofed tokens appearing within hours of hyped launches, states that the call is free and can be called directly without x402, and clarifies the signer boundary (hosted reads never receive keypair bytes). It also discloses the canonical-mint warning behavior. The only minor gap is that it doesn't describe pagination behavior in detail, but the cursor parameter and the 'max 200' limit are mentioned. This is strong behavioral disclosure for a read-only list tool.

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?

The description is dense but well-structured: it front-loads the core purpose and return fields, then lists optional filters, then gives the canonical-mint warning, then the execution guidance. Every sentence earns its place. It is longer than the minimal two-sentence example, but the extra length is justified by the security warning and the SAP MCP execution guidance, which are genuinely useful for an agent. It loses one point for being somewhat verbose and for including the SAP MCP execution guidance block that is also repeated in the input schema description, which is redundant.

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 read-only list tool with a rich output schema, the description is complete. It covers what the tool returns, the optional filters, the pagination mechanism (cursor, limit max 200), the exclusion of core assets, the security warning about spoofed mints, and the execution context (free, direct call, signer boundary). The output schema exists, so the description doesn't need to explain return values in detail. An agent has everything it needs to decide whether to call this tool and how to invoke it correctly.

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 100%, so the schema already documents all four parameters (limit, cursor, symbol, assetClass) with descriptions. The description adds meaning beyond the schema by explaining the semantics of the symbol filter ('case-insensitive symbol substring filter') and the assetClass enum values, and by noting the limit max of 200. It also adds the important context that USDC/USDT/WETH/WBTC are not in the list, which affects how an agent interprets the symbol filter. The description doesn't repeat the schema verbatim but adds useful context, so it earns above the baseline 3.

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 states a specific verb ('List'), a specific resource ('Sunrise-supported tokens on Solana'), and the exact fields returned (symbol, name, decimals, assetClass, tokenProgram, issuer, icon). It also distinguishes itself from sibling tools by noting that USDC/USDT/WETH/WBTC are core assets NOT in this list but quotable, and by referencing sap_sunrise_resolve_token as the alternative for resolving mints. This is a clear, specific purpose that an agent can act on 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 description explicitly states when to use this tool: to list all Sunrise-supported tokens and to resolve canonical mints. It also gives an explicit exclusion: USDC/USDT/WETH/WBTC are not in this list but are quotable, so an agent knows not to look for them here. It names the alternative (sap_sunrise_resolve_token) and provides a strong security guideline: never trust mints from social media or DEX search results. This is explicit when/when-not guidance with alternatives.

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