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

With no annotations, the description carries the full burden and delivers: the key is shown once (non-recoverable), nothing is signed or paid, what the response contains (api_key, tenant.id, keys live/sandbox, cockpit_url, next_steps), the auth header to use (X-API-Key), and the counter behavior versus the per-IP visitor budget.

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?

Front-loaded with 'START HERE' and dense with actionable content, but it crams conditional instructions, a literal example payload, and raw endpoint paths into one paragraph. Every sentence earns something, though the structure is closer to a wall of text than a clean brief.

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?

With no annotations and no output schema, the description still fully equips the agent: return fields, endpoint, header convention, rate-limit context, and next steps are all covered. Nothing needed to call it correctly is missing.

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% and both params are optional, so baseline is 3; the description adds genuine meaning by clarifying both are mere labels, that no arguments are needed, and that wallet_address involves no signing. It goes slightly beyond the schema descriptions rather than merely restating them.

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?

States a specific verb+resource+outcome: 'Get a free Taifoon key in one call' and explains it onboards a TENANT via POST /v1/register. An agent can immediately distinguish this from siblings like taifoon_tenant (read-only) or taifoon_agents_register without opening a schema.

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 unusually explicit routing: 'START HERE', names the immediate follow-up (taifoon_post_demand), the reader for your own numbers (taifoon_tenant), and states this is where a 429 rate-limit points. It does not, however, distinguish itself from the similarly named sibling taifoon_agents_register or state a 'don't call if you already have a key' exclusion.

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