dry_run_tool

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

No annotations provided, so description carries full burden. It fully discloses the behavior: runs stored code, requires only sample input, stamps version, clears dry_run_required blocker, and that editing afterwards bumps version and invalidates proof. Also documents expected refusal scenarios.

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 somewhat verbose but each sentence adds significant value. It front-loads the core purpose and then provides important usage and caveats. Could be slightly trimmed without loss, but overall 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?

Despite lacking an output schema, the description covers the tool's effect on state (version stamping, blocking clearing), failure modes, and relationships with editing and publishing. It provides complete context for correct usage.

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%, providing baseline of 3. Description adds meaning beyond schema for 'inputParams' by advising to give realistic input and noting that a run never reaching real work still stamps version, which is helpful for effective use.

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's purpose: 'Prove a SAVED tool by running its OWN stored code in the sandbox.' It distinguishes itself from sibling execute_tool by explaining that the code is not supplied by the user, making it the legitimate publish gate run.

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?

Explicitly explains when to use (after last edit to satisfy publish gate) and when not (editing afterwards invalidates proof). Also details error codes for inappropriate use (403 for locked tools, 422 for connectors or empty implementations), providing a clear alternative (execute_tool).

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