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

Annotations only declare readOnlyHint=true; the description adds genuinely new behavior: the data is a fixed historical snapshot (Olympia end), results are sorted by stake descending, each row includes the delegator's share of the validator's stake, and paging is offset-based. It does not state whether a total count or next-page indicator is returned, which matters for offset pagination.

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?

Four short sentences with no filler; the snapshot scope and ordering are front-loaded where the agent needs them. The opening fragment lacks a verb, which slightly weakens the first read, but nothing is wasted.

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?

With no output schema, the description does carry the return-shape burden and partially meets it (delegator plus stake share, in descending order). It omits pagination completeness signals such as total delegator count or an end-of-results indicator, and says nothing about behavior for a non-validator or non-Olympia address.

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%, so address, offset, and limit are already documented, and the description's 'Paginated with offset' plus the stake-descending ordering adds some interpretive context for how offset behaves. It does not add constraints (e.g., 100 max limit) or clarify that the address must be an Olympia-era validator beyond the schema's rv1… hint.

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?

Names the specific resource (a single Olympia validator's delegators) and pins it to a precise point in time ('when Olympia ended'), which clearly separates it from olympia_get_validator and olympia_list_validators. It reads as a noun phrase rather than a verb+resource statement, but the resource and scope are unambiguous.

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 explicit when-to-use or when-not-to-use guidance, and no mention of the sibling tools that return validator-level or current-era data. The 'when Olympia ended' snapshot implies a historical look-up use case, but the agent is left to infer that this is not for current stake.

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