forge_draft

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

Annotations declare readOnlyHint=false and openWorldHint=true, implying mutation and external access. The description confirms live verification when url is provided and mentions returning {score, rows}. However, it does not disclose side effects like memory consumption, potential overwrites, or access requirements beyond what annotations hint. The description adds some value but lacks depth for a tool that modifies state.

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 two sentences, starting with a clear action-oriented purpose. All critical information (input modes, behavior modes) is included without redundancy. Every phrase adds value, making it highly efficient.

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 5 parameters (none required), no output schema, and complex two-mode behavior, the description covers the main scenarios: with url (verification) and without (stashing). It explains the two input options and their relationship. However, it could be more complete by clarifying what 'stashes the draft' means in terms of state persistence or lifetime.

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 has 100% coverage; each parameter is described. The description adds context about the preferred usage of plan over code and explains the url behavior. However, it does not significantly enhance understanding beyond the schema, and the parameter 'description' is mentioned without additional semantic value. Baseline of 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 tool loads a tap into memory and optionally verifies it live. It specifies two input modes (plan and code) and differentiates behavior based on url presence. However, it does not explicitly differentiate from sibling tools like tap_run or tap_list, leaving some ambiguity about when to use this tool over others.

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 explicit guidance on when to use url (auto-run verification) and when not (stash draft). It also indicates a preference for the plan parameter over legacy code. While it doesn't explicitly mention alternatives or when-not-to-use, the context of the tool (loading draft) is reasonably clear from the description.

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