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

With no annotations, the description carries the full behavioral burden and does disclose that data is live ('right now'), sourced from RPC, and mainnet-only, plus that it reaches back to the last epoch for ejections. It says nothing about rate limits, caching/staleness, failure modes, or cost of the call. So it adds meaningful context but leaves operational behavior undisclosed.

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?

The resource is front-loaded and the returned fields are grouped logically, which is good structure. But the second sentence drifts into marketing cadence ('what someone choosing where to stake wants to know') and the semicolon-chained clauses make it denser than needed. Tightening would improve scanability without losing information.

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 two-parameter read tool with no output schema and no annotations, the description does the heavy lifting by enumerating the returned fields and the two operating modes. An agent knows what it will get in each case. The only gap is behavioral detail around freshness and limits, which is secondary here.

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 both parameters are already documented, warranting the baseline 3. The description does contribute framing the schema lacks: that `account` switches the tool into a single-pool mode returning rank, work, fee and vote, and that `limit` selects by stake ranking. That is value on top of the schema, but no format or edge-case detail beyond it.

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 names a specific resource (NEAR mainnet validators from RPC) and enumerates what it returns: stake share, epoch work done, protocol version, and last-epoch ejections with reasons. It also distinguishes the two modes (list vs. single pool lookup), so an agent can tell what it gets. It stops short of explicitly naming a sibling it should be preferred over, e.g. get_network_state or get_protocol_status.

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 an implied rule: pass a pool account for per-validator detail, omit it for the list, reinforced by the framing 'what someone choosing where to stake wants to know'. That is a real use-case cue. However, there is no explicit when-not-to-use guidance and no comparison against adjacent tools like get_network_state, leaving routing to inference.

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