Check the status of a running Ghost Audit. Pass the audit_id returned by ghost_audit_site. Returns status: 'complete' when the full markdown report is ready to download, or 'running' with elapsed time. Poll every 15-30 seconds after starting an audit. Typical completion time: 60-120 seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| audit_id | Yes | The audit_id returned by ghost_audit_site |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that the tool returns status and elapsed time, and that 'complete' indicates the report is ready to download. No annotations provided, so description carries full burden; it adequately describes the polling behavior and no destructive side effects. Could mention any rate limits or authentication needs, but not critical for this simple tool.
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?
Four sentences, all essential. No redundant information. Purpose is front-loaded in the first sentence, and each sentence adds value (how to use, output, polling guidance, timing).
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?
Given the tool's simplicity (1 required parameter, no nested objects, no output schema), the description provides complete coverage: input source, output states, and usage pattern. No gaps remain for an agent to understand how to use it correctly.
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% with a single parameter audit_id described as 'The audit_id returned by ghost_audit_site'. The description adds the phrase 'Pass the audit_id returned by ghost_audit_site', which reinforces but does not significantly extend beyond the schema. Baseline 3 is appropriate.
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 verb 'check' and the resource 'status of a Ghost Audit'. It specifies the input (audit_id from ghost_audit_site) and the output (complete/running with elapsed time). This distinguishes it from siblings like ghost_audit_site and ghost_audit_report.
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 advises to poll every 15-30 seconds after starting an audit, and gives typical completion time (60-120 seconds). This tells the agent when to use the tool and how often to poll, including implied when not to use (before an audit is started).
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 have distinct purposes, but there are several overlapping or redundant tools (e.g., leadsignal vs leadsignal_generate, multiple code audit tools, multiple trading proposal/journal tools, and several 'universal' entry points like zambo_help, zambo_ask, zambo_universal). Descriptions help, but the volume creates ambiguity.
Naming conventions vary across prefixes (zambo_, zambot_, axis_, presence_, trading_, etc.), with some tools using single words (weather, translate) and others using verb_noun patterns. Aliases like leadsignal_generate for leadsignal break consistency. While prefixes provide some grouping, the overall pattern is mixed.
125 tools is excessive for a single MCP server, even if the server aims to be a universal stack. This makes it overwhelming for agents to navigate and increases the likelihood of misselection. Many tools could be split into domain-specific servers.
The tool surface is extraordinarily comprehensive, covering agent identity, cross-layer orchestration, code analysis, content generation, legal scanning, lead generation, trading, on-chain data, and more. Nearly any common agent task is supported with multiple tools, leaving few obvious gaps.