Call a tool on the official hosted Avalanche MCP

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds valuable context beyond that: it is a network call to a specific endpoint (inducing potential rate limits), and it lists specific remote capabilities. It also notes the 'always-current' nature of docs_search, which is extra behavioral info. No contradiction with annotations.

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, tightly written paragraph. The core purpose is front-loaded, followed by a scoped use case list and a fallback rule. Every sentence carries meaning, with no filler. The structure makes it easy to scan and extract the essential decision logic.

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 proxy tool with only two parameters and no output schema, the description covers the key aspects: URL, when to use, specific tool examples, and rate-limit handling. It does not detail the return format, but given the open-ended nature of proxying (output varies by called tool), this is acceptable. The description could mention that the output is tool-specific, but the absence is a minor gap.

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 (name and arguments) are already documented. The description adds a critical semantic hint: 'pass chainId as a STRING' for build_plan, which clarifies a type requirement not present in the generic schema. It also gives examples of valid tool names, aiding correct invocation. This goes beyond the schema's generic descriptions.

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 is a proxy to Ava Labs' hosted Avalanche MCP, with a specific verb ('proxy a tool call') and resource (the hosted MCP URL). It explicitly lists the tool names it is best for, distinguishing it from the many local sibling tools. This is unambiguous and immediately separable from alternatives.

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?

Guidance is explicit: 'Best for things the local index lacks' and a concrete list of tools, plus a clear fallback instruction ('On 429 fall back to local tools'). This tells the agent exactly when to use this proxy versus local tools, and even provides a contingency for rate limits. It names alternatives implicitly by contrasting with 'local tools'.

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