Metis — Review Open Decisions

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

With no annotations, the description carries the full burden. It does disclose a non-obvious behavioral trait — results are sorted by how often a decision was restated — but never states that this is a read-only operation with no side effects, nor what happens when state is set to 'all' versus a specific state.

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?

Front-loaded with the action and the ordering rule, and the rationale sentence for the ordering earns its place by explaining why ordering is by repetition. The Args block is compact. Slight cost from the poetic framing, but nothing is wasted.

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?

An output schema exists, so return values need not be described, and both parameters are covered. What is missing is whether the repetition ordering applies across all state values or only 'open', and confirmation that the call is non-mutating — a gap that matters given zero annotation coverage on a decision-related tool.

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 coverage is 0%, so the description must compensate, and it does for the important case: it enumerates the six valid state values (open | agreed | rejected | deferred | dropped | all) that the schema only types as a bare string. 'limit: How many to show' is thin but serviceable for an integer.

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?

States a specific verb and resource ('walk the decisions waiting on you') plus the distinctive ordering rule ('most-repeated first'), which an agent cannot infer from the name. It stops short of naming how it differs from sibling decision tools like recall_decisions, show_agent_decisions, or resolve_decision, so sibling differentiation is left to inference.

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?

'Decisions waiting on you' implies a review workflow, and the default state of 'open' reinforces that this is for pending items. However, there is no explicit when-to-use versus recall_decisions (retrieval) or resolve_decision (mutation), and no statement of exclusions or preconditions.

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