patch.never_branch

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The phrase 'when supported' hints at conditional behavior (i.e., it may fail on some architectures), which is useful but vague. It does not disclose what happens on failure, whether it modifies instruction bytes or metadata, or if it is reversible. A 3 is reasonable because it offers some insight beyond a tautology but lacks specifics.

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 a single sentence of 7 words, extremely concise. It conveys the core action and a key condition ('when supported'). All information is front-loaded. However, it could still improve by being more informative without sacrificing brevity.

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 the moderate complexity (mutating operation, dependency on architecture support, two required parameters with no documentation), the description is insufficient. It lacks details on return values, failure modes, parameter semantics, and the meaning of 'supported'. The context signals indicate high schema coverage gap (0%), no output schema, and many sibling tools—demanding richer description.

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?

The schema has two required parameters (session_id, address) with 0% description coverage. The description does not add any meaning to these parameters—e.g., what session_id refers to, what address format is expected, or any constraints. Neither schema nor description explains these, leaving the agent guessing. Baseline would be 4 with 0 params, but here there are 2 params with no help.

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 states 'Patch conditional branch to never branch when supported.' This clearly identifies the verb (Patch), the resource (conditional branch), and the intended effect (never branch). However, it does not differentiate from sibling tools like patch.always_branch, patch.invert_branch, or patch.convert_to_nop, which share similar patching semantics.

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 no guidance on when to use this tool versus alternatives like patch.always_branch, patch.invert_branch, or patch.convert_to_nop. There is no mention of prerequisites, such as requiring a valid session or a specific address, nor any context about when it's appropriate or not to use this tool.

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