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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), yet the description adds genuinely useful behavioral facts: values are percentages (16.08 means 16.08%), no dollar amounts are returned, and figures are pre-computed rather than calculated on request. Since no output schema exists, the unit disclosure is the key piece of return-value context and it is supplied. It stops short of describing result shape or what happens with partial/absent parameters.

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 short sentences with the core purpose front-loaded and the source attribution parenthesized out of the way. The second sentence is mildly redundant ('values are percentages' and 'no dollar amounts' say nearly the same thing), but the unit example is worth the extra clause.

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 simple two-optional-parameter read tool with no output schema, the description covers units and source, which is the main risk. However, both parameters are optional and the description never says what the default behavior is (all metrics? all tiers?), and it gives no hint about the shape or size of the result set. That leaves a real gap for an agent calling it with no arguments.

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 schema already documents both parameters, including that metric ids come from the `metrics` tool and that asset_tier labels match `tier`. The description only restates 'by asset tier' and adds no syntax, default behavior, or interaction rules. Baseline 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?

States a specific resource and scope: pre-computed peer-group benchmarks for credit unions broken out by asset tier, sourced from NCUA. It is clearly distinct from per-institution tools like credit_union or credit_union_trends, but it never names a sibling alternative (e.g. industry_benchmarks, peer_comparison) so the differentiator is inferred rather than declared.

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 implied rather than stated: 'pre-computed peer-group benchmarks ... by asset tier' suggests this is the tool for aggregate tier-level comparison rather than single-credit-union lookups. There is no explicit when-to-use, when-not-to-use, or named alternative among the many peer/benchmark siblings, so an agent must infer the boundary itself.

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