Metis — Set Focus State

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

With no annotations, the description carries the full burden and does so: it discloses that nothing is deleted, that archived is read-only with no refresh, that downstream content (notes, ideas, papers, briefs) keeps its tags and is untouched, and that moves can be refused with an explanation. That is unusually complete behavioral and safety disclosure for a mutation tool.

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, then a tight state table, then args and returns. The "Removing a lens cannot remove what you saw through it" line is a rhetorical flourish, but it reinforces the non-destructive guarantee rather than padding, and total length stays modest.

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-parameter mutation tool with no annotations, the description covers what changes, what does not change, the capacity limit, the failure mode, and even names the return payload — with an output schema already present to detail the shelf layout. Nothing an agent needs to call this correctly is missing.

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% — both `slug` and `state` are bare strings with no descriptions or enum — so the description must compensate, and it does: `state` is documented as active | following | archived with full semantics for each value. The only gap is `slug`, which gets a one-line gloss ("The focus slug") but no format or where-to-obtain-it detail.

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?

Opens with a specific verb and resource ("Move a focus between the shelf, following, and the archive") and immediately enumerates the three target states, so an agent knows exactly what the tool does. It never names the adjacent siblings (create_focus_area, show_focus_areas, focus_keep/focus_decline), so the differentiation is left to inference rather than stated.

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?

Each state is given a concrete operational meaning ("on the shelf and in the left navbar", "defined and queryable, off the navbar", "read-only, no refresh, still openable"), which is exactly the guidance needed to pick a value. The hard constraint ("At most 3") is stated up front, though there is no explicit when-not-to-use or pointer to an alternative tool.

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