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

Annotations already cover read-only, idempotent, closed-world behavior, and the description adds genuinely new context: the data source is lenders' Open Banking product data, the snapshot date is 2026-10-27, lender names are masked, and a warning must accompany results. These are facts the agent could not derive from the annotations, though it does not state result ordering, pagination, or what happens when no products match.

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?

Two sentences, no filler. The operational scope (product type, rate basis, LVR, recency, masking) comes first and the mandatory presentation rule second, which is the right priority order for an agent.

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?

The description covers the data provenance, freshness, anonymization, and the required warning, which is substantial for a tool with no output schema. However, it leaves the purpose (owner vs investment) and limit parameters entirely unexplained and gives no sense of result shape beyond 'each rate with its comparison rate', so an agent must guess at two of three inputs.

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 only 33%: lvr is documented in the schema, while limit and purpose are not. The description restates the LVR scoping (no added syntax or semantics) and never clarifies the owner/investment purpose enum or what limit controls. With two of three parameters undocumented, the description fails to compensate for the coverage gap.

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 concrete verb/resource pair — live variable principal-and-interest home loan rates with comparison rates, scoped to a given LVR — drawn from lenders' Open Banking product data. The scope qualifiers (variable, P&I only, LVR-based) make the tool's purpose unambiguous, though it never names or distinguishes itself from the sibling tools, which happen to cover clearly different domains (stamp duty, deposit scheme, broker referral).

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?

Usage is only implied: the agent must infer that this tool is for rate-listing at a specific LVR. There is no explicit when-to-use/when-not statement and no routing to alternatives such as assess_home_loan_readiness or refer_to_broker. The one directive present ('Always show the comparison rate beside each rate, with the warning returned') is an output obligation rather than a selection guideline.

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