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

Beyond the readOnly, idempotent, and non-destructive annotations, the description discloses data-retention behavior: Stackcut stores tool-call arguments, hashes account keys, never stores IP addresses, and warns against sending personal data or secrets. This is valuable behavioral context not present in annotations.

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 front-loaded with the use case and outputs, then adds a privacy notice. The privacy sentence is long but relevant; there is no filler, though it could be tightened without losing meaning.

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?

It covers outputs, fallback behavior, and privacy constraints, while annotations cover the safety profile. The main gaps are explicit recipe_id semantics and a detailed return structure, but for a single-parameter read-only tool it is largely 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?

Schema description coverage is 0%, and the description never names recipe_id or explains how to supply it. It only implies the tool operates on a recipe, which is insufficient for a required parameter with no schema-level documentation.

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 what the tool does: returns SPEC.md, AGENTS.md, and runbook files for recipes with a build path, and assessment files for recipes without one. It is tied to the 'Replace with AI' use case, but it does not explicitly name or differentiate sibling tools like get_recipe.

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?

It opens with 'Use when the user wants to replace a tool by building their own' and instructs the agent to check packet_kind and next_step before acting. However, it does not mention alternatives or exclusion conditions, so it stops short of full routing guidance.

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