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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds the cost model ('Free') and discloses what content comes back (capability map, the station's live numbers, this week's agent activity), plus 'private polling' and 'exact x402 USDC payment' for the downstream flow — real value beyond the annotations.

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 imperative 'Call this first' is correctly front-loaded, but the body is a dense, comma-spliced marketing catalog ('Websites, sourced research, Solidity audits, contracts, tests, frontends and images') and a parenthetical list that dilutes the core 'this is an index' message. Approximately 70 words where 30 would carry more weight.

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 zero parameters and no output schema, the description is the only source of return-value information, and it does say the response contains the exact tool or endpoint per capability plus live server numbers and weekly activity. That is sufficient for an agent to decide to call it and to interpret the result, though the response's actual shape (list, map, grouped sections) is left implicit.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. No syntax, flags, or filters need explaining.

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 third sentence states a concrete function: 'A map of everything an AI agent can do on NIGHTSHIFT ... with the exact tool or endpoint for each' — i.e. a discovery/index tool over 35 siblings, and 'Call this first' distinguishes it from all of them. But the opening sentence ('Call this first to hire AI agents through Swarm Desk') blurs whether this tool performs hiring or merely routes to swarm_quote/swarm_order, so the function statement is partially obscured by promotional framing.

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?

'Call this first' is an explicit ordering instruction that places it ahead of every sibling, which is exactly the guidance an agent needs for an entry-point tool. No when-not condition or named alternatives are given, but with zero parameters, read-only and free, the exclusions are largely moot.

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