Get the pending validators of a Subnet/L1 (paginated; use limit/offset)
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max items to return (default: 50). Use with "offset" to page. | |
| offset | No | Number of items to skip from the start (default: 0). | |
| network | No | Avalanche network to query (default: mainnet) | |
| nodeIDs | No | Optional list of node IDs to filter by | |
| subnetID | No | The Subnet ID to query pending validators for (default: Primary Network) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It does mention pagination ('paginated; use limit/offset'), which is a useful behavioral trait, but it does not disclose other behaviors such as return format, sorting, default subnet behavior, or any potential side effects (though as a 'get' operation, it is likely read-only). The disclosure is minimal but not absent.
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 description is a single, front-loaded sentence: 'Get the pending validators of a Subnet/L1 (paginated; use limit/offset)'. Every word contributes meaning, with no redundancy or fluff. It is highly concise and well-structured.
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?
Considering the tool has 5 optional parameters, no annotations, and no output schema, the description adequately covers the core purpose and mentions pagination. It does not explain the concept of 'pending validators' or explicitly state that the result is a list, but the tool name and sibling context make this fairly obvious. For a simple getter, this is reasonably complete.
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?
The input schema has 100% description coverage for all five parameters. The description adds a brief instruction to use limit/offset for pagination, but this information is already clearly embedded in the schema's parameter descriptions. Thus, the description adds marginal value beyond the schema, matching the baseline for high schema coverage.
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 clearly states the tool retrieves pending validators for a Subnet/L1, using a specific verb ('Get') and a precise resource ('pending validators'). It distinguishes itself from sibling tools like platform_get_current_validators by explicitly focusing on 'pending' 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?
The description implies usage through the word 'pending', but it does not explicitly mention when to use this tool versus alternatives like platform_get_current_validators. No direct exclusions or alternative references are provided, making the guidance only implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools are redundant due to compatibility aliases (avalanche_docs_* vs docs_*, blockchain_get_* vs onchain_lookup) and overlapping functionality (chain_stats vs onchain_query, onchain_activity vs onchain_query ops, acp_list vs info_acps). Agents may struggle to select the correct tool when multiple appear to serve the same purpose, despite descriptions clarifying aliases.
Naming patterns are inconsistent: some tools use noun_verb (acp_list, docs_fetch), some use verb_noun (build_plan), and others use prefixes like platform_get_, info_get_, and onchain_. The mix of styles (snake_case, noun phrases, verb phrases) makes it hard to predict tool names.
With 48 tools, the count is high and inflated by compatibility aliases and granular platform_get_* wrappers. The scope spans multiple domains (docs, on-chain, platform API, ACPs, console), which could be better modularized. Many tools are trivial variants (e.g., platform_get_block vs platform_get_block_by_height) adding unnecessary bulk.
The server provides thorough read-only coverage for Avalanche: docs search, ACP management, on-chain lookups, indexed stats, platform API getters, and console flow guidance. While there is no transaction submission (likely intentional), the surface covers most queries a developer would need, with minor gaps like detailed token transfer history.
