Metis — Get Persona Learnings

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

With no annotations, the description carries the full disclosure burden. "Show" and "Returns" strongly imply a pure read with no mutation, and the return contents (lessons with evidence and dates) are described, but there is no explicit statement of safety, side effects, empty-result behavior, or cost.

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?

Four short sentences, purpose front-loaded, then usage, then Args and Returns headers. Nothing redundant and structure maps directly onto what an agent needs to decide and call.

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?

Covers purpose, when to invoke, parameter values, and return contents; with an output schema present it need not document return shape in more detail. The only real gap is behavioral disclosure left unfilled by the absent annotations.

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 has no enum, so the description is the only place the valid `category` values (voice, workflow, preference, avoid, domain) appear — that is genuinely load-bearing information. It also marks the parameter optional but does not state the default effect of omitting it.

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?

"Show what Metis has learned about how to behave" states a concrete verb and resource, and the Args/Returns block makes the object of the read unambiguous. It is clearly the read counterpart to `record_persona_learning`, though it never names that sibling to sharpen the contrast.

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 three explicit triggering contexts: at session start alongside `metis-persona.md`, when the researcher asks what Metis has learned, and when auditing whether a rule still holds. That is strong positive guidance, but there is no stated exclusion or named alternative for any situation.

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