Metis — Show Agent Decisions

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the return structure (grouped, with categories and apply counts) and offers an interpretive framing about unapplied decisions, but never states that the operation is read-only/side-effect free and gives no auth or limits 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?

Front-loads the core question and the key interpretation of `applied` before the args block, which is good ordering. The Returns section is partly redundant given an output schema exists, and the rhetorical opening costs a sentence, but nothing is badly padded.

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?

For a two-optional-parameter read tool with an output schema, the description covers purpose, both parameters, and the shape of results adequately. The main gap is routing among the numerous decision-related siblings, which the description never addresses.

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 largely does: agent_slug is explained as a restrict-to-one-specialist filter with the omit-for-all default, and limit as maximum rows. It stops short of saying where valid slugs come from or noting the schema's default of 30.

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 concrete resource (standing decisions carried by an agent) and what the output reveals (whether they are applied), which is more than a restatement of the name. It does not distinguish itself from the many decision-related siblings (recall_decisions, review_open_decisions, record_decision), so an agent must infer the boundary.

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?

Gives useful in-tool guidance: "Pass no slug to see every decision" and the framing that the `applied` count is the signal to interpret. However, there is no statement of when to reach for this tool versus recall_decisions or review_open_decisions, nor any prerequisite or exclusion.

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