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

With no annotations, the description carries the full behavioral burden. It usefully discloses the scoring methodology, weights, and that rationale is sourced, but says nothing about read-only status, data recency/freshness, or how scores relate to incident data available via sibling tools.

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?

It leads with the rubric and weighting, then states the use cases and return format. The per-dimension percentages are dense but substantive for interpreting the scores, and nothing is redundant. Only the weighting rationale sentence ('entropy... cannot be protected by anything downstream') is arguably expendable.

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 single-parameter, no-output-schema read tool, the description covers what is scored, how it is weighted, when to call it, and what comes back. The remaining gap is sibling disambiguation, which matters given several adjacent custody-comparison 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?

Schema description coverage is 100%, and the single 'device' parameter is documented in the schema with examples and an omit-for-all rule. The description adds no parameter-level detail beyond the general phrase 'per-device', so the baseline 3 applies.

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 makes clear that this tool returns hardware wallet scores under a defined rubric and states its output ('per-device sourced rationale'). It does not, however, distinguish itself from siblings like compare_custody_platforms or assess_custody_independence, even though the 'X vs Y device' phrasing invites overlap.

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?

Concrete trigger queries are given ('best hardware wallet', 'X vs Y device', what to replace a device with), which is strong usage context. There are no exclusions or explicit alternatives named, so an agent gets no help disambiguating this from compare_custody_platforms.

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