set_demo_wallet

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

The description greatly expands on the annotations (idempotentHint=true, non-destructive). It explains that setting a wallet upgrades demo mode to live mode, where prepare/simulate/preview tools run real state and send_transaction returns a simulation envelope. It also notes that multiple per-cell calls accumulate but same chain replaces, and that custom addresses are read-only. All behavioral traits are disclosed, far exceeding annotation information.

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 verbose (about 200 words) but well-structured with sections, bullet points, and examples. Every sentence adds value, though a slightly more concise version could be written. The front-loading is good: the first sentence explains the core function. Overall, it's appropriate for the complexity of the tool.

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 tool's complexity (three input shapes, multiple chains and types, demo mode behavior), the description is complete. It explains the effect on other tools, advises to call get_demo_wallet first, and covers edge cases (clearing wallet, no-op outside demo mode). No output schema is needed as the tool's effect is described in behavioral terms.

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 coverage is 100%, but the description adds extensive meaning: it explains the three mutually exclusive input shapes, provides examples for each, and clarifies nuances like cell accumulation, replacement, and null cells. It also describes the purpose of each parameter field (chain, type, persona, custom) beyond the schema descriptions, making parameter usage very clear.

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 states the tool's purpose: to switch the active demo wallet using one of three input shapes (chain+type, persona, custom). It distinguishes from siblings by explaining that setting a wallet upgrades demo mode from default to live, and that calling outside demo mode is a no-op. The verb 'set' and resource 'demo wallet' are specific, and the description covers the three distinct input shapes, making it unambiguous.

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 explains when to use the tool ('DEMO MODE ONLY') and provides detailed guidance on when to use each input shape: per-cell loader for single chains, batch loader for convenience, custom for arbitrary addresses. It also states when not to use it (outside demo mode) and what happens (no-op). No alternatives are explicitly named, but the tool is unique for setting demo wallets, and the description contrasts with default demo mode behavior.

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