Metis — Open Output

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

With no annotations, the description carries the burden well: it discloses the side effect (each file launches in its own Windows application such as PowerPoint, Word, or the browser) and a path restriction. It omits failure behavior for missing or non-existent paths and whether the call blocks until the app opens.

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?

Purpose is front-loaded in the first line, and the args block adds only information the schema lacks. The parameter name is restated in the args header, a small redundancy, but no sentence is wasted.

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; the description covers what the tool does, when to call it, where paths come from, and the outputs/ restriction. Edge cases (invalid path, partial failure across multiple files) are the one gap.

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% and the schema only declares a bare string, so the description must compensate — and it does: one or more paths, newline or comma separated, taken verbatim from the writing tool, with a concrete example and the note that Windows paths are also accepted.

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 ('Open files Metis created') plus concrete examples of the artifacts (decks, posters, letters, figures) and the destination (researcher's screen). It is clearly distinguishable from list_outputs, which only enumerates what exists.

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?

'Call this at the end when the researcher asks to see, show or open what was made' gives an explicit trigger, and 'Only files under outputs/ can be opened' sets a hard eligibility boundary. It does not name alternatives (e.g. read_file for reading contents rather than launching), so it falls just short of a 5.

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