Return a deep-link into a specific Builder Console flow (create-l1, convert-to-l1, validator-manager, ictt, faucet, multisig, staking, transfers, interchain-kit-local). For faucet on mainnet, returns a note that there is no mainnet faucet.
| Name | Required | Description | Default |
|---|---|---|---|
| flow | Yes | The console flow to link to | |
| network | No | Network (only affects faucet; default: fuji) | |
| validatorManager | No | Validator-manager variant (default: poa) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It states return type (deep-link) and special case for mainnet faucet, but does not describe format of the link or any side effects.
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?
Single sentence with parenthetical addition. Front-loaded with main purpose, no superfluous words.
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, description does not specify return format (e.g., URL string, object). For a simple tool, it covers essential behavior but could be more explicit about output.
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%, baseline 3. Description adds context: list of flows, notes that network only affects faucet, and validatorManager variant. Adds value beyond enum names.
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?
Clear verb 'Return a deep-link' with specific resource 'Builder Console flow' and lists all valid flows. Distinct from sibling tools which are info/lookup.
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?
Explicitly lists valid flows and special behavior for faucet on mainnet. No explicit comparison to alternatives, but context suggests no direct sibling is similar.
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.
