Launch a discovery run

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

Goes well beyond the annotations (destructiveHint=true, openWorldHint=true) by naming the concrete consequence: real money is spent, capped at 500 credits, and already-delivered accounts are skipped unless excludeSeen=false. It also discloses the return shape and the required follow-up calls, which the annotations cannot convey.

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?

Four short sentences with the money warning front-loaded in caps. Every clause carries a distinct fact (cost, cap, exclusion behavior, return + follow-up) and none restates the schema.

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?

Covers cost, exclusions, return value and the polling chain, which is strong for a 2-param nested-object tool with no output schema. The one gap is the slug playbook enum: eleven modes are offered with no hint that the playbook list must be consulted first.

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 description adds real semantics for the two highest-stakes parameters: creditsCap is required, capped at 500, and must be agreed with the user; excludeSeen defaults to true and behaves differently for enrich-known-list. It also names the return contract { runId }.

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?

Opens with a specific verb+resource ("Launch a discovery run") and immediately qualifies the kind of run — credit-spending, profile-scanning — which separates it from siblings like estimate_credits or get_run_results. An agent can identify the tool's role without opening the 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 the operational sequence (agree creditsCap with the user first, then poll get_run_status, then read get_run_results) and states a prerequisite for the expensive case. It never explicitly routes to estimate_credits for a cost preview, which is the most relevant sibling, so it stops short of full when/when-not guidance.

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