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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description's job is to add specifics — and it does: MAINNET, the 60/15/25 default split vs. 60/15/5/20 with referral, required env keys, optional approval, and the 'Check feeShareLocked' caveat. It stops short of stating that a launch is irreversible or what happens on partial failure, but the added context is well 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?

Six short clauses, zero filler, and the MAINNET warning plus crew[] preference are front-loaded ahead of the key/approval details. The telegraphic semicolon-heavy style is efficient, though slightly compressed for a 20-parameter mainnet mutation.

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 destructive mainnet launch with 20 params and no output schema, the description covers the critical operational facts: network, fee-share defaults, key requirements, approval path, and the feeShareLocked follow-up. Return values are not described, but the absence of an output schema means the agent can't rely on a structured contract for them, leaving a minor gap.

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?

With 20 parameters at 65% schema coverage, the schema carries most of the load and the description only supplements it, notably explaining crew[] as the preferred source and the fee-share arithmetic. It adds nothing about initialBuySol, mode, seats, idempotencyKey, or the forbidden-secret parameters that the schema already flags. Adequate but not compensating for the coverage gap.

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 ('Creates a Pump.fun coin with on-chain fee-shares') and immediately flags MAINNET, so the agent knows this is a real-value launch rather than a dry run. It also routes between the two crew-sourcing paths (explicit crew[] vs. Autohire), which cleanly separates it from crew_autohire and crew_launch_dry_run.

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 explicit preference guidance: 'Prefer explicit crew[] (from crew_list_kols). Autohire is a fallback convenience,' which names the source tool and the alternative path. It also states prerequisites (CREW_AGENT_API_KEY + CREW_LAUNCHER_KEY) and that approval is optional, though it never tells the agent to run crew_launch_dry_run first or when to prefer crew_build_unsigned/crew_submit_signed.

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