One-shot retrieval of the plaintext for a successor minted by the auto-rotation scheduler (not by rotate_api_key — that returns its own plaintext directly). Decrypts the at-rest ciphertext, returns it once, then destroys it; a second call errors. Only available while the predecessor still has an unrevealed successor.
| Name | Required | Description | Default |
|---|---|---|---|
| keyId | Yes | UUID of the predecessor key whose successor to reveal. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotation Contradiction: The description states that the tool 'returns it once, then destroys it; a second call errors,' which indicates a destructive, state-changing operation. However, annotations declare readOnlyHint=true and destructiveHint=false, directly contradicting the described behavior. Per rubric, a contradiction merits a score of 1 regardless of descriptive richness.
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 dense sentences communicate purpose, exclusions, one-shot behavior, destruction, error on second call, and availability precondition. No filler or repetition; every clause adds value.
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?
Description covers all critical context: one-shot retrieval, return value (plaintext), destruction semantics, second-call error, availability condition, and differentiation from rotate_api_key. Even with no output schema, the return type is clear from the description.
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 the parameter description 'UUID of the predecessor key whose successor to reveal' already providing clear semantics. The description adds minimal extra meaning beyond clarifying that the successor comes from auto-rotation. Baseline 3 is appropriate when schema fully covers parameters.
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?
Description specifies a specific verb and resource: 'One-shot retrieval of the plaintext for a successor minted by the auto-rotation scheduler.' It explicitly distinguishes itself from rotate_api_key, which returns plaintext directly. This makes the tool's purpose unambiguous and differentiates it from siblings.
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 states when not to use this tool ('not by rotate_api_key') and gives an availability condition ('Only available while the predecessor still has an unrevealed successor'). This provides clear guidance on when to invoke the tool versus alternatives.
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.
Most tools target distinct resources and the descriptions are unusually explicit, but the billing cluster (change_plan/cancel_subscription and the many add-on actions) plus the preview/diff tools overlap and could cause mis-selection. config_diff, dry_run_endpoint, and preview_line_draft all read as 'preview what will change' at first glance despite different scopes.
The overwhelming majority follow a clean snake_case verb_noun pattern: create_*, get_*, list_*, set_*, update_*, delete_*. It is only held back by a few naming outliers such as config_diff and default_endpoint_template, which break the verb-first convention.
78 tools is an extreme mismatch for an MCP server surface, even accounting for the broad management/relay domain. Such a large surface will overwhelm model context and make tool selection materially harder; this would be better split into focused servers for configuration, data-plane operations, and billing.
The tool surface is very thorough: projects, lines, endpoints, credentials, keys, configs/drafts, DLQ, requests, metrics, audit, team, and billing are all represented. Only minor gaps exist, such as no direct single-line get/update and the intentional inability to widen the outbound allowlist or lift archive protection via API.
