continuum_run_auditAn observability readiness audit that scores eight self-declared continuity capabilities without fetching evidence or invoking a model.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_name | Yes | ||
| categories | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already indicate readOnly and idempotent behavior, and the description adds that it does not fetch evidence or invoke a model, reinforcing the non-destructive, side-effect-free nature. This goes beyond the annotations by clarifying the absence of external calls and model inference, which is valuable for an agent deciding whether to use it.
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, compact sentence with no redundant words. It efficiently communicates the core function and key constraints (self-declared, no external fetching, no model invocation) without any fluff.
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?
The description provides sufficient context for an agent to understand the tool's purpose and limitations, especially given the schema details. It does not describe the output format or scoring methodology, but since there is no output schema, and the tool's behavior is straightforward, the description is reasonably complete for typical use.
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 description alludes to the 'categories' parameter by mentioning eight capabilities, but it does not explain the purpose of 'agent_name' or the meaning of the 'level' and 'evidence_url' sub-fields beyond what the schema already shows. The self-declared aspect is hinted at, but parameter semantics are only partially enriched.
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 function: it performs an observability readiness audit that scores eight self-declared continuity capabilities. It distinguishes itself from sibling tools (e.g., checkout, sponsor packet) by being an audit, so an agent can easily identify its purpose.
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 useful guidance by stating that the audit is based on self-declared capabilities and does not fetch evidence or invoke a model. This implies it is a lightweight, non-verifying check, suitable when quick assessment is needed. It doesn't explicitly contrast with alternatives, but the nature of the operation is clear enough.
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 serves a clearly distinct purpose: creating a checkout, creating a sponsor packet, fetching an offer, registering a referral, and running an audit. There is no overlap between their responsibilities, making misselection highly unlikely.
All tool names follow a consistent verb_noun pattern in snake_case: create_checkout, create_sponsor_packet, get_offer, register_referral, run_audit. The naming is uniform, predictable, and easy to parse for an agent.
With 5 tools, the server is well-scoped for its purpose. Each tool covers a distinct workflow step, and there is no bloat or redundancy. The count fits comfortably within the ideal 3-15 range.
The tool set covers the core lifecycle: creation (checkout, sponsor packet, referral), lookup (offer), and validation (audit). Minor gaps exist, such as no update/cancel for created entities, but the essential workflow appears functional without dead ends.