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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint. The description adds real context beyond them: initialize/tools/list work key-free while tools/call needs Bearer nak_, a 50-credit trial, USDC-on-Base pricing, and the no-custody/key guarantee. Missing are return shape, rate limits, and proxy failure 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?

A single dense paragraph mixing branding, affiliation disclaimers, endpoints, auth, pricing, custody policy, and proxy internals. The operational core (view semantics) is buried at the end rather than front-loaded, and marketing phrases like 'No earnings promises' do not help selection.

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 2-parameter discovery tool with no output schema, the description should clarify what catalog and the proxied reads return and what happens when NOID_KIT_ENABLED is off. It instead spends its length on service marketing and pricing, leaving the agent's understanding of the response incomplete.

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 the view enum is documented in-schema. The description reinforces that whale_moves/new_tokens hit CrewPay proxies gated by NOID_KIT_ENABLED and that view selects them, but adds no format or failure semantics. Baseline 3 is appropriate.

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 names a specific resource, CrewPay's NOID Agent Kit, and lists the services it fronts (checkout invoices, receipt verification, whale/new-token alerts, launch checklist). But the tool's own action is opaque until the buried sentence 'this tool can request them via view='; the reader cannot tell whether crew_noid returns a catalog card or performs the reads.

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?

Explicit 'When to use: Parano1d checkout, alerts, or a launch checklist' and 'When not to use: Solana coin launches, human escrow jobs, or launch art (crew_creative)' - the exclusion names the sibling to route to. This is strong when/when-not coverage, though it doesn't explain how it differs from crew_discover.

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