forge_draft

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

Annotations (readOnlyHint:false, destructiveHint:false, openWorldHint:true) indicate mutation and side effects. The description adds context about loading into memory and running verification, but does not disclose whether existing drafts are overwritten, the lifespan of the draft, or details of the verification process. Adequate given annotations, but more would be helpful.

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 four sentences, no filler. It front-loads the main action, then details inputs, then conditional behavior. Every sentence adds value.

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?

With 5 parameters, no output schema, and nested objects, the description covers the two main workflows but lacks details on what 'stashing the draft' means, how to retrieve it later, or typical usage patterns (e.g., followed by forge_save). Adequate but could be more complete given the complexity.

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 100%, so baseline is 3. The description adds value by explaining the relationship between 'plan', 'code', and 'url' parameters (e.g., 'preferred over code', 'auto-runs verification when url provided'), which goes beyond individual schema 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 tool loads a tap into memory and optionally verifies it live. It distinguishes two modes (with/without url) and two input types (plan vs code). However, it does not explicitly differentiate from sibling tools like forge_inspect or forge_save, leaving some ambiguity.

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 explains when to provide a url (for live verification) and when not to (just stashing). It also notes the preferred input method (plan over legacy code). It does not list explicit exclusions or alternatives, but the context is clear enough for an agent.

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