OCI MCP Server

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Start an instance' implies a mutation operation but reveals nothing about side effects (e.g., billing implications, startup time), permissions required, error conditions (e.g., invalid instance_id), or response format. It lacks critical details like whether the operation is idempotent, asynchronous, or has rate limits, making it inadequate for safe and effective use.

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 extremely concise ('Start an instance.'), which is efficient but borders on under-specification. It consists of a single sentence that is front-loaded with the core action, but lacks necessary elaboration. While brevity is not inherently problematic, the content is too sparse to be helpful, failing to provide the context needed for effective tool use.

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 complexity of starting an instance (a mutation with potential side effects), no annotations, no output schema, and minimal parameter documentation, the description is severely incomplete. It omits essential information such as behavioral traits, usage prerequisites, error handling, and return values. For a tool that likely interacts with cloud infrastructure, this level of detail is insufficient for reliable agent operation.

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 input schema has 1 parameter with 0% description coverage, and the tool description adds no information about the 'instance_id' parameter. It does not explain what an instance_id is, how to obtain it (e.g., from 'get_instance' or 'list_instances'), its format, or validation rules. With zero schema coverage and no compensatory details in the description, parameters are effectively undocumented.

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 'Start an instance' is a tautology that merely restates the tool name without adding meaningful context. It specifies the verb ('start') and resource ('instance'), but lacks specificity about what kind of instance (e.g., compute instance, database instance) or what 'starting' entails. Compared to siblings like 'start_db_node' or 'start_db_system', it fails to distinguish itself clearly, leaving ambiguity about its exact scope.

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 no guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., instance must be stopped), exclusions (e.g., cannot start if already running), or related tools like 'stop_instance', 'reboot_db_node', or 'get_instance' for checking status. Without such context, an agent cannot make informed decisions about its applicability in different scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.