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

Adds substantial context beyond annotations: upfront credit charge, async behavior with concrete timings (~2-5 min at max_pages=200, 30+ min at the Pro 1,000-page default), and the poll target. Annotations already flag destructive/openWorld/idempotent, but the description never explains what the destructiveHint or idempotentHint actually mean for this job, so it is strong rather than complete.

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?

Two dense sentences, front-loaded with what runs and where it runs, followed by cost and async timing. Every clause earns its place; it is information-dense but not padded.

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 output schema, the description correctly discloses that results arrive asynchronously via get_prospect_audit and gives expected durations and billing behavior. It omits any notion of what the destructive/idempotent hints imply, but an agent has enough to invoke and follow up correctly.

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%, so baseline is 3, but the description adds useful meaning: max_pages=200 vs the 1,000-page Pro default ties directly to the stated runtime estimates, and it confirms competitor_domains auto-discovery. The agency_notes/style_reference round-trip semantics are left to the schema.

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 ('start_prospect_audit' / 'Client Pro SEO Audit of a domain') and enumerates scope (crawl, PageSpeed, backlinks, competitor keywords, AI-visibility). The phrase 'a domain that has connected nothing' cleanly separates it from audits of connected properties, and it names the get_prospect_audit sibling for polling.

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?

Explains the condition that selects this tool (a prospect domain with nothing connected, charged upfront from Assist credits) and tells the agent to poll get_prospect_audit. It does not explicitly contrast against create_audit or start_crawl, so routing is clear but not exhaustive.

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