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

Annotations cover the safety profile (readOnlyHint=true), and the description adds real context: the wait_seconds mechanism blocks up to 60s and returns the full report the moment the scan finishes. It does not disclose polling/timeout failure behavior, but the added value is genuine.

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 sentences, no waste, and the state enumeration plus the wait behavior are front-loaded so an agent can decide immediately whether to wait.

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 usefully notes that a completed wait yields the full report, and it lists the terminal states. It could say more about what a non-complete status returns, which is the main remaining 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?

Schema description coverage is 100%, so both parameters are already documented, and the description largely restates the wait_seconds cap. The 'returns the full report as soon as it does' phrasing is return behavior rather than added parameter semantics, so baseline 3 is right.

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 ('Status of a scan') and enumerates the possible states (queued, scanning, analyzing, complete, failed), which makes it clearly distinguishable from siblings like get_report or list_recent_scans.

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?

Usage is implied by the wait_seconds behavior (poll after scan_url), but the description never says when to use this rather than get_report or list_recent_scans, nor when not to wait. Adequate but no explicit routing guidance.

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