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

Annotations declare a write (readOnlyHint=false, idempotentHint=false) but the description adds real behavioral detail beyond them: the one-row-per-measure-and-year uniqueness rule, the 409 duplicate outcome, and the required los_proposed_targets:write scope. An agent knows both the failure mode and the auth prerequisite before calling.

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 short sentences with no filler: what it records, the cardinality constraint, the error/uniqueness behavior, the field-choice rule, the scope, and the prerequisite. Front-loaded with the purpose and the operational constraint.

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?

For a 4-param write tool with no output schema, the description covers everything an agent needs: uniqueness semantics, duplicate handling, auth scope, field selection, and the lookup prerequisite. No return-value explanation is required since no output schema exists.

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 baseline is 3, but the description goes further by explaining the semantic split between target_statement (community measure) and target_value (technical measure) and by flagging los_measure_id as an FK to resolve first. That is genuine added meaning over the schema's field descriptions.

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 and resource ('Record the proposed level of service for a LoS measure in one future year') and anchors it to the regulatory clause O. Reg. 588/17 s. 6(1). It also pins the granularity ('one row per measure and year'), which an agent can use to distinguish it from other LoS writers, though it never names the nearby siblings (create_infrastructure_los_target, create_system_los_target).

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?

Gives explicit when-to-use routing: resolve los_measure_id first via list_los_measures, use target_statement for a community measure vs target_value for a technical one, and if a duplicate returns 409, update the existing row instead. That names the alternative tool (update_los_proposed_target) and the condition that selects it.

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