pr_memory_review

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

With no annotations, the description carries the full burden. It uses 'finds' and 'flags', which imply a read/analysis operation without side effects, and adds context that it enables the AI to supersede/update memories later. It does not explicitly state that the tool itself never mutates memory, but the wording strongly suggests it is diagnostic. This is adequate but not fully explicit, so a 4 is appropriate.

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 with no wasted words. It front-loads the purpose and effectively conveys both the action and the intended outcome. Every clause contributes to understanding.

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?

The description covers the core behavior and context (current branch diff, base_ref, memory filtering). Since an output schema exists, return values don't need explanation. It could optionally note that it does not modify memories, but that is implied. Overall, it's nearly complete for an agent to decide whether to call it.

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 only parameter, base_ref, is referenced in the description as the comparison base for the diff, giving it functional meaning beyond the schema (which has no description and a default of 'main'). This compensates for the 0% schema coverage, making the parameter's role clear. However, it doesn't explain format or allowed values, which is minor given the default.

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 function: reviewing the current branch diff against a base_ref, and then finding memories touching changed files and flagging those likely obsolete. It uses specific verbs ('Review', 'finds', 'flags') and distinguishes itself from sibling tools like search_memory or log_decision by focusing on PR context. An agent can immediately grasp what it does and why it is unique.

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 implies usage (use when you want to review a diff for memory obsolescence) but does not explicitly state when to prefer this over alternatives, nor does it mention exclusions or when not to use it. It lacks direct comparison to siblings like recall or search_memory, so the agent must infer the appropriate context.

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