Metis — Promote Session Decisions

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

With no annotations, the description carries the full behavioral burden and does well: it discloses fingerprint deduplication, the resulting times_seen aggregation, and that resolved rows are untouched so reruns are safe. It omits cost/latency implications of scanning up to 2000 summaries and any permission or write-scope detail for the ledger mutation.

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 in the first sentence, followed by the two behavioral facts that matter most for safe reruns. The args block is minimal and nothing is padded, though the dedup explanation runs slightly long for what it conveys.

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 no explanation, and the description covers the mutation's key semantics (dedup, idempotency, resolved rows untouched). For a one-parameter tool with zero annotations it is nearly complete; what is missing is scale/cost guidance and its relationship to the sibling decision tools.

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 0% and the schema only says integer with default 2000, so the description's 'how many recent session summaries to scan' is the sole source of meaning and genuinely compensates. It still gives no sense of the tradeoff at the default value or what a lower limit sacrifices.

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: pulling decisions out of session summaries into the open-decisions ledger. That is concrete and distinguishable in substance, but the description never names or contrasts the very similar siblings commit_session_decisions, review_open_decisions, or resolve_decision, so the agent must infer the division of labor.

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?

Usage is only implied: the agent must already know it has session summaries worth mining. The line about re-running never reopening a closed call is useful rerun guidance, but there is no explicit when-to-use versus when-not, and no pointer to the closely related decision-ledger tools despite a crowded sibling set.

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