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

Annotations already cover the safety profile (readOnly, idempotent, open-world, non-destructive), so the bar is lower, and the description adds genuinely new context: the effective defaults (min_cluster_size 2, similarity_threshold 0.95) and the fact that a disabled clustering service returns status 'disabled' with no families. It does not discuss cost, latency, or result volume.

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 filler, with the core semantics front-loaded and the exceptional service state placed last. Slightly dense parenthetical phrasing but every clause carries information.

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 described, and the description covers the clustering semantics, the two tunable thresholds, their defaults, and the disabled-state edge case. The only gap is the undocumented limit parameter and any expected result-size guidance.

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 carries the burden. It explains min_cluster_size ('clusters of at least min_cluster_size scans'), similarity_threshold ('0 to 1, default 0.95'), and supplies effective defaults the schema leaves as null – but the third parameter, limit, is never mentioned or constrained.

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 names a specific verb and resource ('List groups of scans whose runtime JavaScript behaves alike') and clarifies the concept as 'possible malware families', which distinguishes it from hash- or signature-based siblings. It does not explicitly name a sibling it must not be confused with (e.g. search_js_runtime_similar), so an agent still has to reason about the boundary itself.

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 concept of clustering scans into families, but there is no explicit when-to-use/when-not-to-use statement and no routing to alternatives like search_js_runtime_similar. The one piece of conditional behavior given – clustering switched off – is about the service state, not about tool selection.

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