review_decision

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

Annotations already provide idempotency and safety signals (idempotentHint=true, destructiveHint=false, readOnlyHint=false), and the description does not contradict them. It adds the evidence-source constraint but does not disclose side effects or what happens to the decision record upon review, which is relevant given it is not marked read-only.

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, front-loaded sentence with no fluff. It states the action, the object, and the evidence constraint efficiently.

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?

Despite having an output schema, the tool has 18 parameters and 6 required inputs, indicating a complex workflow. The one-sentence description omits prerequisites (e.g., an existing recorded decision), the meaning of terminal-link evidence, and the effect of a review on the decision state, leaving a significant gap.

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 hint is 'terminal-link evidence', mapping to terminal_evidence_refs. With schema coverage at 33%, many optional parameters (e.g., alignment, causal_strength, safety_signal) are unexplained in both the description and the schema; the description does not compensate by explaining how the required parameters interrelate.

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 this tool reviews exactly one decision ('Review one decision') and scopes the evidence to MCP-created terminal-link evidence ('using only MCP-created terminal-link evidence'). This distinguishes it from sibling tools like record_decision or propose_lesson by making the subject and evidence type explicit.

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 phrase 'using only MCP-created terminal-link evidence' provides a clear usage constraint: this tool should be invoked only when such evidence is available. However, it does not name alternatives or explicitly state when not to use it, leaving some ambiguity about the workflow context.

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