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

With no annotations, the description carries the full burden and does so well: data source (Unity Nodes Pulse), freshness ('snapshot refreshed every 15 minutes'), a data-quality warning ('Monikers are typed by the validators and marked untrusted'), and an interpretation caveat ('a validator missing a signature is not necessarily down' because Celestia commits at two thirds of voting power). These are non-obvious behavioral traits an agent cannot get from the schema.

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 purpose and return fields, then filters, sort, and caveats. Most sentences earn their place, though the two-thirds-of-voting-power explanation and the missed-proposal health note are somewhat verbose relative to selection needs.

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 exists, so the description correctly enumerates the returned metrics and names the data source and refresh cadence. It omits any note on pagination semantics for the 100-cap default-25 list, which is a minor remaining gap for a list tool.

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 67%, so the description must compensate for gaps, but it largely restates what the schema already documents (status enum meanings, sort fields, mainnet/mocha). The limit/offset pagination parameters receive no explanation in the description, leaving the remaining undocumented portion unaddressed.

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 and resource (list Celestia validators) and enumerates the exact metrics returned (status, voting power, stake, commission, missed proposals over 24h/7d/30d, 30-day VP change). It explicitly distinguishes the tool from its closest sibling by saying 'Use get_celestia_validator for one validator' and by noting 'Celestia validators only,' separating it from list_fibre_validators.

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 concrete selection context: 'Filter by status or name; sort by voting power, commission, missed proposals or voting-power change,' and routes single-validator lookups to get_celestia_validator. There are no explicit when-not-to-use exclusions (e.g., versus get_celestia_network_health or get_celestia_decentralization), so it stops just short of full guidance.

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