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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavior: k-anonymity thresholds (k=5, k=10) and the folding of the sub-k tail into 'other', edge caching, keyless-cacheable access, and 'Names no operator' as a privacy guarantee. It stops short of describing latency or staleness semantics beyond 'computed live'.

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?

It is a single dense paragraph that front-loads a vague heading ('Software landscape') before the real content. Almost every clause carries information, but the parenthetical density and unexplained jargon ('two-denominator coverage block', 'no bare coverage scalar') cost readability without a clear structural hierarchy.

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 carries the burden of explaining the return and does so thoroughly: vendor share, version distribution, ASN share, and the two named denominators (~90% host-weighted, ~50% participant-weighted). The main gap is the absence of any statement about the time window covered or how it relates to the history variant.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly adds no parameter framing and instead spends its words on output content, which is the right allocation for a parameterless read tool.

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 resource and enumerates its contents: k-anonymised vendor share (k=5), version distribution per vendor (k=10), ASN hosting share, and a two-denominator coverage block. It does not, however, name or contrast itself against the obvious sibling get_software_stats_history, leaving the live-vs-historical distinction to inference from 'Computed live'.

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?

There is no explicit when-to-use statement and no named alternative. The only routing clue is the indirect 'Computed live from the temporal software table and edge-cached', which an agent could read as a contrast to the history sibling, but this is never stated. An agent must infer selection from the sibling list alone.

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