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

With no annotations, the description carries the full burden and does substantial work: it names the data source (Unity Nodes Pulse), states a 15-minute snapshot cadence, notes bridge nodes are mainnet only, and discloses a real accuracy limitation — host names come from a network crawl and can be wrong behind sentries. It stops short of covering auth, rate limits, or result size, so it is strong but not complete.

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?

Front-loaded with the payload contents, followed by scope/network constraints, freshness, caveat, and alternative. Dense but each clause carries information (the crawl caveat and mainnet-only bridge note especially). Slightly long single-sentence opening, but no filler.

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?

No output schema and no annotations, so the description must cover returns, scope, and caveats on its own — and it does, enumerating the returned fields, the supported networks, the refresh cadence, the known data-quality caveat, and where to go for the adjacent use case.

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% for the single 'network' param, so the description must compensate, and it does: it explains the mainnet/Mocha choice and flags the non-obvious constraint that bridge-node data is mainnet only. Only the enum values themselves are restated by the schema, so the added semantics are meaningful.

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 verb+resource (celestia decentralization: validator voting-power concentration and DA) and enumerates exactly what comes back — hosting providers, countries, unknown-host voting power, and public bridge nodes with status/version/uptime/host. It is clearly separable from siblings like get_celestia_network_health, list_celestia_validators, and get_celestia_validator.

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?

Gives an explicit routing rule for one scenario: 'To choose where to run a node use list_datacenter_providers.' It also bounds scope with 'Celestia only, a snapshot refreshed every 15 minutes.' However, it never says when NOT to reach for this versus get_celestia_network_health or the validator-listing tools, so the guidance is good but not exhaustive.

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