Live sample: who can actually move funds out of one fixed Gnosis Safe -- owners, threshold, and modules expanded recursively, because a Safe that reads as 1-of-1 can in fact be governed through a module by a separate 2-of-8. The paid GET /safe-signer-drift takes any Safe and adds what changed and in which block.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses key behavior: recursive expansion, the module-governance nuance (1-of-1 appearing but actually 2-of-8 via module), and that it is a live sample. It does not explicitly state read-only status, but the 'sample' context implies safety, and the added nuance provides value beyond what annotations would.
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 two sentences, front-loaded with the main purpose, and includes a valuable comparison to the paid alternative. Every clause serves a purpose; no redundancy or filler.
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 zero-parameter sample tool with no output schema, the description is remarkably complete. It covers the fixed scope, recursive expansion, a critical nuance, and even points to the paid tool for expanded needs. No significant gaps remain.
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 tool has zero parameters, so the description need not explain any. The baseline for 0 params is 4, and the description adds no unnecessary parameter details, allowing the score to stand.
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's purpose: to show who can actually move funds from a fixed Gnosis Safe, including owners, threshold, and modules expanded recursively. This distinguishes it from sibling tools by focusing on Safe governance and from the paid tool by framing it as a sample.
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 provides usage context by contrasting with the paid GET /safe-signer-drift: this sample covers one fixed Safe, while the paid tool accepts any Safe and adds change details. It does not explicitly compare to sibling sample tools, but their different domains make this omission acceptable.
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 targets a distinct financial check (DAO governance, lending depeg, oracle staleness, Safe authority, vesting status), and the catalog serves as the index. No two tools overlap in purpose or output.
Five tools follow a clear 'noun_sample' pattern, but the catalog breaks the pattern with a prefixed name 'apix402_catalog', creating a minor inconsistency. Still, all names are snake_case and readable, so the deviation is small.
With only 6 tools, the set is compact and each tool represents a specific sample category plus a catalog entry point. This is an appropriate size for a preview-oriented MCP server.
The catalog lists all available checks, and the five samples cover key verticals (governance, lending, oracles, safe custody, vesting). The only gap is that paid endpoints are not exposed as MCP tools, but that is by design since payment occurs over HTTP.