custom_nodes

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state that validate_icon is used 'before creating/updating', giving a workflow hint, and the operation names (delete, update) are relatively self-explanatory. However, it does not mention side effects such as permanence of delete, whether updates are immediate, or any permission/authorization requirements. This is a moderate gap for a management tool with destructive operations, so a 3 is appropriate.

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?

Although the description is relatively long, it is well-organized into a summary line, an info_type list, and an args list. Each line conveys necessary information without redundancy. The structure front-loads the core purpose then details each operation and its parameters, making it easy for an agent to scan and extract relevant details. It is appropriately sized for a tool with 10 parameters and 9 operation modes.

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 thoroughly covers the operations and their required parameters, which addresses the main selection and invocation concerns. However, since there is no output schema, it does not describe what the tool returns for each info_type (e.g., whether list returns an array, whether get returns a config object). This would be valuable for an agent to know the outcome. The description is otherwise complete for the tool's complexity, so this is a minor gap.

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 schema provides no descriptions (0% coverage), so the description fully compensates. It explains each of the 10 parameters, including their purpose and the info_type operations they are needed for (e.g., 'kind_name: Custom node kind name (for get, update, delete)'). This adds substantial meaning beyond the schema's bare titles and defaults, giving the agent all required context for invocation.

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 opens with a specific verb phrase 'Manage OpenGraph custom node display configs and v9 extension schemas', identifying both the resource and action. It also enumerates all info_type operations (list, get, create, update, delete, etc.), making the tool's scope unmistakable and distinguishing it from sibling tools that focus on other entity types (e.g., group_info, computer_info).

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 clearly explains the usage by listing each info_type and the required arguments for each operation, which serves as a mini-guide for when to use which sub-operation. However, it does not explicitly state when not to use this tool or mention alternatives, nor does it contrast with sibling tools. The context of being the tool for custom node/extension configuration is implied but not spelled out in comparison form.

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