add_task_node

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

With no annotations provided, the description carries the full burden. It discloses a critical behavioral trait: it validates dependency references and checks for cycles before inserting. This goes beyond the basic 'add' action and informs the agent about potential rejection errors. However, it does not describe what happens if validation fails or how the graph is persisted, leaving some transparency 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 exactly two sentences: the first front-loads the primary action and context, and the second adds the key validation behavior. Every word is purposeful; there is no fluff, repetition, or extraneous detail. It is concise and well-structured.

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 13 parameters and no output schema, the description covers the core purpose and validation but leaves important gaps. It does not mention what the tool returns (e.g., the created node or updated graph), what happens if validation fails (beyond 'checks before inserting'), or whether the graph must already exist. These details are relevant for an agent using the tool with complex state and no structured output guidance.

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 54% (7 of 13 parameters have descriptions), so the description must add some value. It notes that phase and category are optional, and it explains that dependency references are validated, which gives meaning to the depends_on parameter. However, it does not add semantic context for many parameters like priority, max_attempts, or output_artifacts, leaving the burden on the schema or the parameter names themselves.

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 ('new task node'), and the target context ('into the active workflow graph'). It distinguishes itself from siblings like update_task_node and reset_task_node by specifying 'new' and 'dynamically'. The added clauses about dependency validation and cycle checking further clarify the tool's specific role.

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 implies this tool is for creating new nodes but does not explicitly mention when to use it over alternatives such as update_task_node or reset_task_node. It provides context ('dynamically', 'active workflow graph') but lacks explicit exclusions or naming of alternative tools for comparison.

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