Metis — Focus Explore

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

With no annotations, the description carries the full burden, and it does usefully disclose that the tool is read-only retrieval and does not synthesize an answer. It says nothing about scope limits, what happens if the focus area's corpus is empty, permissions, or whether the corpus is bounded to the focus area only.

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?

Two short sentences with zero filler, and the retrieval-only constraint is front-loaded immediately after the purpose so it cannot be missed.

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 the two params are self-describing in name. The essential behavioral fact an agent needs — that this gathers rather than answers — is stated explicitly. Only minor gaps around slug acquisition remain.

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. It implicitly clarifies that slug identifies a focus area and that question is posed against that area's corpus, which is real added meaning, but it gives no format guidance, no indication of how to obtain a slug, and no sense of question phrasing expectations.

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?

The description gives a specific verb+resource pairing: answer a question against a focus area's own corpus, notes and ideas. It is meaningfully more precise than the name alone, though it never names the sibling it differs from (run_metis, focus_brief, preview_focus_lens) so the boundary is inferred 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?

'Retrieval only — this returns the material, it does not compose the answer' implicitly tells the agent to pick this over a composing tool when raw material is wanted, but no sibling is named and no prerequisites (e.g. that the focus area must already exist, or that a slug comes from show_focus_areas) are given.

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