memory_check_change

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

No annotations are provided, so the description carries the full burden. It clearly establishes this is a pre-edit check and states what it returns (a decision and matching memories), implying a read-only, non-destructive operation. It doesn't explicitly state side-effect-free, but 'check' and 'return a decision' strongly imply no mutation. Slightly better if it stated 'does not modify anything'.

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 purpose-built sentences: the first states what the tool does and what it returns (decision types), the second states the exact call condition. Front-loaded with 'Pre-edit safety check'. No wasted words.

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?

4 params fully covered in the schema registered at 100% coverage)Skip. The description adds the decision semantics (proceed/ask_first/stop) and the before-editing usage contextcars. A safety-check tool with no output schema benefits from the explicit return value list, which it provides. Slightly light on what 'matching' means (keyword/path matching), but the schema's param descriptions handle that.

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?

Every parameter (diff, task, paths, agent_id) is described in the schema with 100% coverage, so the baseline is 3. The description reinforces purpose (diff vs task/paths matching) but doesn't add semantics beyond the schema. Acceptable but not additive.

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 names the exact verb ('check'), resource ('FAILED_APPROACH, GUARDRAIL, INVARIANT, or CONVENTION memories'), and the decision output (proceed, ask_first, stop). It also distinguishes the matching scope (diff or task/paths), so an agent knows exactly what this tool does and what it returns.

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 explicitly tells the agent WHEN to call: 'BEFORE editing code' and 'when the task touches an area with known historical failures or explicit rules.' It also explains the diff-or-description fallback semantics. This is prescriptive and the tool names its output decision clearly.

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