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

Annotations already cover readOnly, idempotent, non-destructive and closed-world behavior. The description adds genuine context beyond that: 'at most one open per mandate', that questions are generated by deterministic checks in every household cycle, and the 'Any key role' authorization note.

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, but the first sentence is long and carries parenthetical examples ('a taxable account with no cost basis...') that consume space without helping tool selection. Some sentences earn their place; the examples are borderline noise.

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 read-only, annotated list tool with no output schema, the description adequately explains what questions are, their lifecycle ('at most one open per mandate'), and the available filters. It omits return shape, ordering and pagination, but annotations carry the safety profile so this is close to complete.

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 25% (only api_key documented), so the description should compensate. It names the filterable fields and lists the status enum values, but those values are already in the schema, and it adds no format or meaning for mandate_id/household_id beyond what the schema implies. Partial compensation only.

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 clearly identifies a list operation over 'Lodestar's questions' and even defines what a question is (data gaps flagged by deterministic checks) with concrete examples. It's specific about the resource, though it never explicitly distinguishes itself from the sibling answer_question, which an agent would have to infer from the name alone.

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 states how to filter (status, mandate_id, household_id) and notes 'Any key role', but gives no explicit when-to-use vs. answer_question or other list_* siblings. Usage is implied only by the name and filter hints.

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