Plan And Decompose Feature

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

The description adds useful behavioral context beyond annotations by disclosing atomicity ('Atomically') and the single-turn nature ('in a single turn'), which are important for understanding side effects. Annotations only indicate non-readOnly and non-destructive, so the description's atomicity claim adds value. It does not mention failure behavior or return value, but the core mode of operation is clear.

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, well-structured sentence that front-loads the primary action and resource. Every phrase contributes substantive information (atomicity, single-turn, components), with no redundant or filler content.

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?

For a composite write tool with 5 parameters and no output schema, the description adequately covers what the tool does and its atomic nature. However, it could be more complete by describing expected return behavior or error conditions, and by clarifying the structure of subtasks and dependency edges. Still, given the schema and annotations, it provides sufficient context for most use cases.

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 baseline is 3. The description adds meaning by revealing that dependency edges are created as part of the operation, which is not explicitly present as a parameter in the schema. It also clarifies the optional milestone, which maps to milestone_title, enhancing parameter understanding beyond the schema's generic descriptions.

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 verb 'create' and the resource 'feature plan', and enumerates the specific components it handles (milestone, subtasks, dependency edges). This distinguishes it from lower-level sibling tools like add_node and add_edge by emphasizing atomic, single-turn composite creation.

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 usage for creating a complete feature plan atomically, but it does not explicitly state when to use this tool instead of alternatives (e.g., batch_create_nodes, add_node/add_edge) or when not to use it. No exclusions or alternative guidance is provided.

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