add_child

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

With no annotations, the description is the only behavioral disclosure. It correctly indicates the core mutation (a child is added under a parent) and implies the parent must already exist, but it does not mention side effects, persistence, return value, or whether the operation evaluates or validates the child. This is adequate but carries clear gaps.

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 one short sentence with no filler, redundancy, or buried information. It front-loads the action and resource. For a simple mutation whose parameters are fully documented in the schema, this level of brevity is appropriate.

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 plus the complete schema covers the basic operation and all required parameters. However, with no annotations and no output schema, an agent is left unsure whether the created thought is returned, whether the tree is updated in place, or how sessionId affects the operation. That makes it minimally viable but not fully complete.

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?

Input schema description coverage is 100%, so every parameter — treeId, parentId, content, metadata, sessionId — already has a meaningful description. The tool description adds no new parameter-level meaning, but the schema carries that burden, so a 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 ('Add'), the resource ('a child thought'), and the target ('an existing thought'), so the basic intent is unambiguous. It does not explicitly differentiate from sibling tools like generate_children or generate_and_evaluate_children, which also produce child thoughts. This prevents a 5 but is well above a vague or tautological description.

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 choose add_child over the many related sibling tools. There are no alternatives named, no exclusions, and no stated conditions such as 'use this for a single manual child rather than generated children.' The agent is left to infer selection from the tool name and schema.

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