propose_patch

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

The readOnlyHint annotation already covers the safety profile, and the description adds a critical behavioral fact beyond it: this tool is a non-functional stub that always errors. That single detail reliably prevents wasted invocations.

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?

Two short sentences with no filler, and the failure disclosure is placed immediately after the purpose so an agent sees it before deciding to call.

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 no-param, no-output stub, the description conveys everything an agent needs to make the call/no-call decision: what it is and that it is guaranteed to fail. Only the absence of a recommended alternative keeps it from a 5.

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?

Zero parameters, so there is nothing for the description to document; the baseline for a 0-param tool applies.

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 expands the name ('propose_patch' → 'Request a Proposed Patch') and, more usefully, states that it is not implemented. However, it does not differentiate this tool from the sibling suite (create, validate, inspect, etc.) or explain what a Proposed Patch is.

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 gives an explicit 'when not to use' signal — 'always returns an error' tells the agent to avoid this call entirely, which is the most important routing guidance for a stub. It stops short of naming alternatives (create, validate) that might substitute.

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