memory_critique

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

No annotations are provided, so the description carries the burden of disclosure. It explains that the tool is grounded in verified memory and not another model's opinion, and implies it reports guardrail violations and contradictions. However, it does not explicitly state the return format, whether the tool is read-only, or any side effects. This is a gap, but the description does provide some behavioral context.

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 three concise sentences, front-loaded with the main purpose. Every sentence adds value: the first states what it does, the second gives the critical timing, and the third reinforces the priority. No fluff or repetition.

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 tool's simplicity (2 params, no output schema), the description provides strong contextual guidance about when to call it and its grounding. It implies results will identify violations and contradictions, but it does not explicitly describe the return value or format. A richer description of the output would make it complete, but the current level is adequate.

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%, so the schema already fully documents both parameters. The description adds little beyond the schema for parameters; it echoes the summary purpose ('what you just did or plan to do') but does not provide new parameter-level insight. Baseline 3 is appropriate.

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: 'Review what you just did (or plan to do) against the project's VERIFIED memory and guardrails.' It uses a specific verb ('Review') and resource ('VERIFIED memory and guardrails'), and differentiates itself from sibling tools by calling itself a 'second critic' grounded in 'real, falsifiable beliefs rather than another model's opinion'.

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 gives explicit guidance on when to use the tool: 'Call BEFORE committing or proposing memories.' It also instructs to 'Resolve guardrail violations and contradictions first,' which clarifies the intended sequence. This distinguishes it from alternatives like memory_write or memory_propose.

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