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

Annotations already declare read-only, idempotent, non-destructive and open-world, so the bar is lower; the description nonetheless adds real behavioral context by disclosing that the cell's own tokens are verified against the chain while a third party's are reconstructed from Transfer events within a lookback window, which signals result completeness depends on that window. It stops short of stating rate limits, failure modes, or what happens if the lookback is too short.

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 is a single economical sentence with no padding, but the colon-and-appositive fragment structure reads as an internal note rather than a front-loaded statement of what the tool does, forcing the reader to reconstruct the action.

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?

An output schema exists, so return-value detail is not required, and annotations cover the safety profile. Still, for a two-parameter tool with zero schema descriptions, the definition leaves the default behavior of both optional parameters underspecified, which is a meaningful gap for an agent deciding how to call it.

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 0%, so the description must carry the meaning, and it does explain the semantic role of both parameters (holder selects whose tokens; the lookback window bounds the Transfer-event scan). However, it never states the default when holder is omitted, that lookbackBlocks is measured in blocks and capped at 100000, or what happens to the window for the cell's own configuration path.

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 identifies the resource (skill tokens held by a holder) and distinguishes two derivation modes, but it is a noun-phrase fragment with no explicit verb, so the agent must infer that this is a listing/enumeration operation. It does help separate this tool from skill_inspect in spirit (list vs. inspect), though it never names that sibling.

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: including a holder means querying another holder's tokens via Transfer events, omitting it means reading the cell's own configuration. There is no statement of when to prefer this over skill_inspect, no note about prerequisites such as chain access, and no explicit instruction on defaulting behavior.

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