bolna_add_custom_llm

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

No annotations are provided, so the description carries the full burden. It states the integration is for agents but does not disclose behavioral traits such as whether the operation is reversible, if duplicate model names are allowed, what happens if the API base is unreachable, or any authentication requirements beyond the optional API key in schema. The description is too minimal to be transparent.

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 brief sentence with no redundancy. It is front-loaded with the action and resource. However, it could be slightly more structured by including a second sentence for usage context. Still, it is concise and gets the main point across efficiently.

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 absence of annotations and output schema, the description is incomplete. It does not explain the outcome (e.g., creates a model resource), how to reference the custom LLM in an agent, or any constraints like API compatibility. For a tool that adds an external integration, more context is needed for an agent 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 description coverage is 100%, so schema already documents all parameters. The description adds no additional meaning beyond 'Integrate a custom LLM'. For example, it does not explain that 'model_name' must be unique or that 'api_base' should be an OpenAI-compatible endpoint (though schema format hints at URI). Hence, 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 action ('Integrate') and the resource ('custom Large Language Model'), and specifies the purpose ('for use in agents'). It is distinct from most sibling tools which are about agents, calls, or other entities. However, it doesn't explicitly differentiate from the similar 'bolna_add_provider' tool, which might also add LLMs.

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?

No guidance on when to use this tool versus alternatives. For example, it doesn't explain when to add a custom LLM via this tool versus using 'bolna_add_provider' or configuring an LLM directly in an agent. There are no exclusions or prerequisites mentioned.

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