page_audit_start_scan

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: it's a scanning operation that returns tracking IDs, has an associated cost ('API COST: 10 credits per scan'), requires waiting for completion ('Wait for progress=100'), and involves follow-up tools for progress checking and result retrieval. The only minor gap is lack of explicit mention about whether this is a read-only or destructive operation, though 'scan' implies non-destructive.

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 description is perfectly structured and concise with zero wasted words. It uses three sentences that each serve distinct purposes: (1) states the core action and return values, (2) provides follow-up guidance, (3) adds cost and completion requirements. Every sentence earns its place and information is front-loaded appropriately.

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?

Given the tool's moderate complexity (scanning operation with cost and async behavior), no annotations, and no output schema, the description does an excellent job covering most contextual needs. It explains the scanning purpose, cost implications, async nature with tracking IDs, and follow-up workflow. The only minor gap is that without an output schema, it doesn't fully describe the structure of returned IDs, though 'pageId and reportId' provides sufficient semantic understanding for an agent.

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 description coverage is 100%, so the schema already documents all 5 parameters thoroughly. The description adds no specific parameter information beyond what's in the schema. According to scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no param info in the description, which applies here.

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 clearly states the specific action ('Scan a single webpage with JavaScript rendering') and resource ('webpage'), distinguishing it from sibling tools like 'start_site_audit' (which appears to be for broader site audits) and 'page_audit_rescan' (which implies re-scanning). It explicitly mentions the return values ('pageId and reportId for tracking'), providing a complete purpose statement.

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?

The description provides explicit guidance on when to use this tool ('Scan a single webpage'), when not to use it (implied: not for site-wide audits), and alternatives ('Use page_audit_get_reports_for_page to check progress' and 'retrieving results with page_audit_get_results_report'). It also includes prerequisites ('Wait for progress=100 before retrieving results'), making usage context very clear.

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