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

Annotations already establish the read-only, closed-world, non-destructive safety profile, yet the description goes well beyond that: it discloses that target_hedge_ratio_pct is 0 when unset, that comfort-limit rows with limit 0 are treated as unset and labelled so, and that max_single_trade_base and approval_threshold_base are returned as null with a stated reason. These sentinel-value semantics are exactly the non-obvious behaviour an agent needs to avoid misreading the payload.

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 purpose is front-loaded in the opening clause, which is good, but the remainder is a single dense sentence enumerating stored fields and sentinel rules — much of which restates what the output schema already carries. It is informative rather than padded, but not efficiently portioned.

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?

Since an output schema exists and annotations cover safety, the description need not explain return structure at all; it nonetheless supplies the sentinel semantics that give those returns meaning. The one real gap is the absence of routing guidance against the neighbouring policy/guidance tools.

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?

Only one parameter exists and the schema documents it fully (the entity_id description already explains the omit-for-group-level behaviour), so coverage is 100%. The tool description adds nothing to entity_id, but with the schema doing the work the baseline of 3 is appropriate.

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 first clause states a specific verb and resource — 'Returns the user's saved FX policy in declared form' — which is unambiguous and distinguishable from most siblings like get_fx_exposure or get_hedge_portfolio. It does not, however, explicitly differentiate itself from the closer siblings get_fx_guidance or get_policy_backtest_summary, which an agent might reasonably confuse.

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 statement of when to reach for this tool versus alternatives (get_fx_guidance, get_rate_assumptions), nor any precondition or exclusion. The only routing-like instruction, 'Omit for the group-level policy,' is scoping of the entity_id parameter, not usage guidance.

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