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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), but the description adds real value beyond them: it discloses the polling mechanism, the timeout fallback with timeout=true, and crucially the verdict-pending behavior (verdict fields empty and risk score 0 until the verdict computes, usually within a minute). That timing nuance is not derivable from structured fields.

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 sentences, front-loaded with the core polling/timeout behavior and return semantics, with the verdict caveat following. Every sentence is substantive, though the verdict explanation is slightly verbose relative to the rest.

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?

An output schema exists so return values need not be documented, yet the description usefully summarizes the returned summary fields. Combined with the timeout-fallback and verdict-pending notes, an agent has enough to call this correctly; the only missing piece is explicit routing guidance versus the single-poll and summary siblings.

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 0%, so the description must carry the load, and it largely does: poll_interval_s and timeout_s (default 180) are both explained via the polling sentence, and scan_id is identified as the UUID of a ScanMalware scan. All three parameters get meaningful context, though the units/format of poll_interval_s are only implied.

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 states a specific verb and resource ('Wait for a submitted scan to finish by polling its status') and clearly defines the blocking-wait behavior, which is distinct from single-check siblings like get_scan_progress or get_scan_result. It stops short of naming those siblings explicitly, so differentiation is implied rather than stated.

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 phrasing 'a submitted scan' implies this follows submit_scan, and the timeout semantics imply when to stop waiting. However, there is no explicit guidance on when to prefer this over get_scan_progress (single poll) or get_scan_summary (post-completion fetch), nor any stated prerequisites beyond the implicit submitted-scan requirement.

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