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

Annotations already cover the read-only, idempotent, non-destructive profile, so the bar is lower. The description adds substantial behavior beyond that: derived targets never leave the metric's scale, unrated networks are treated as medium, average risk is unavailable for infrastructure, and the values are not monetary. These are real domain constraints an agent would otherwise have to guess.

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?

Purpose is front-loaded and every sentence carries domain information rather than filler. The modifier arithmetic example ('condition 70 becomes 82 at a Critical network, 58 at a Low one') is the heaviest element and borders on over-explanation for a list tool, but it is genuinely clarifying and the passage remains dense and readable.

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 five optional filters, 100% schema coverage, and no output schema, the description supplies the missing return-shape context: what a base target is, how per-network derived targets are computed, and what metrics exist. Pagination behavior is left to the schema, which documents it, so nothing critical is omitted, though sibling routing remains unstated.

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 coverage is 100%, so the 3 baseline applies; the description goes beyond it by annotating the enum values with directionality and units (fci 0-100 percent lower is better, asset_condition_avg higher is better read with fixed condition bands). It also names three of the five filters explicitly, giving semantic grounding the bare enum list does not.

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 opens with a specific verb+resource ('List technical Level of Service targets for infrastructure') and explains the domain model: one base target per feature class and metric, with derived per-network targets. The 'infrastructure' scoping implicitly separates it from list_system_los_targets, but it never names that sibling or list_los_proposed_targets, so the differentiation is left to inference.

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?

It mentions filtering ('Filter by feature class, metric or active') but gives no when-to-use guidance or alternatives. An agent cannot tell from this text whether to call this versus list_system_los_targets or get_infrastructure_los_target for a single record.

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