Uploads a small base64-encoded object to S3-compatible storage. ~$1/GB, $0.01 minimum, capped at 4MB (larger files: use HTTP PUT /store instead). Returns a key for retrieve_object.
| Name | Required | Description | Default |
|---|---|---|---|
| content_type | No | MIME type, defaults to application/octet-stream | |
| content_base64 | Yes | Base64-encoded bytes to store |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even with no annotations, the description discloses important behavioral traits: approximate cost, $0.01 minimum, 4MB size cap, fallback for larger files, and the returned key's relationship to retrieve_object. This goes well beyond a generic upload statement.
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?
Three short, information-dense sentences. Every clause adds value: pricing, size limit, fallback alternative, and return semantics. No filler or repetition of schema fields.
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 simple two-parameter upload tool with no output schema, the description provides sufficient context: storage target, size constraints, pricing, and the use of the returned key with the sibling retrieve_object 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?
The schema already covers both parameters at 100%, so the baseline is 3. The description adds the 4MB cap for content_base64 and the 'small object' expectation, which is parameter-relevant information not present in the schema.
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?
Clearly names the specific action ('Uploads'), the resource ('S3-compatible storage'), and the key output ('Returns a key for retrieve_object'). It also distinguishes itself from the sibling retrieve_object by describing the write side of the object lifecycle.
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 scopes the tool to 'small' objects and gives a concrete alternative for larger files: 'use HTTP PUT /store instead'. This gives the agent clear when-to-use and when-not-to-use guidance.
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.
Each tool is clearly distinguished by its operation type (network health, priority fee, store, retrieve) and, where applicable, the specific blockchain (Base, Ethereum, Solana). No two tools perform the same function on the same target, so an agent can select the correct tool without ambiguity.
All tool names follow a consistent verb_noun pattern using snake_case. The first six tools use 'get_' plus a descriptive noun (network_health or recommended_priority_fee) followed by the chain name, while the storage tools use 'store_' and 'retrieve_' with 'object'. This predictable convention aids agent selection.
With 8 tools, the server is well-scoped. The six network-related tools cover three blockchains across two recurring operations, and the two storage tools provide minimal yet sufficient coverage. The count is within the ideal range and each tool earns its place.
The network health and fee recommendation tools fully cover their immediate purposes. For object storage, only store and retrieve are provided, lacking delete or list operations. While the core workflow (write and read) is functional, the absence of delete is a minor gap that could require workarounds.