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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the description needn't restate those. It adds real behavioral context: the illustrative asset-location set is labeled not-a-recommendation and never applied silently, alternatives are ranked best-first by a checkable score, deltas name their baseline, every candidate links a verifiable record, and exclusions are stated in the notes. That is strong transparency about output guarantees, though it doesn't cover persistence or whether the call mutates stored state.

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?

The description is a single dense paragraph with a long strategy list run together by semicolons; it is front-loaded with the verb and return, but the parameter recap is hard to scan and duplicates structure that could be a list. It earns its content but not its formatting.

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 seven-parameter, nested, strategy-dispatching tool with no output schema, the description covers every strategy's parameters and the ranking/evidence contract. It omits how the required id, horizon, assumptions, and profile interact with strategy selection, and gives no indication of cost or latency, but the core call is fully specified.

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 only 29%, so the description must compensate, and it does: it spells out per-strategy params for all nine strategies, including candidate objects, optional fields, enum values for bracket-fill, the 62-70 age range for ss-claiming, and peculiarities like the NCHS life table requiring sex for adults. This far exceeds what the bare schema conveys.

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: 'Run a Household Coordination Engine strategy on a stored household' and returns a ranked decision object with evidence records. It distinguishes itself from siblings like run_model or project_household by explicitly naming the strategy set and the ranked-decision output.

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 description enumerates all nine strategies and their parameters, implying when each applies, but it never says when to prefer this tool over alternatives such as run_model or get_decision, nor does it state exclusions or prerequisites (e.g., must the household exist first?). Usage is inferred from the strategy list rather than stated.

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