actions

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

With no annotations, the description carries the load and mostly succeeds: it discloses the return shape (Inkscape's printed output, logged complaints, geometry-changed flag), that a rejected action becomes an error, and that malformed arguments may be silently ignored. It does not flag that this is an unrestricted mutation path that can alter or delete document content, which is a residual safety gap.

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 and dense with no filler; the inline example conveys the run syntax compactly. The telegraphic style ('returning what Inkscape printed, any complaint it logged') is efficient but occasionally terse enough to require re-reading.

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 highly open-ended tool with an output schema, this covers invocation, prerequisites, error semantics, and return shape adequately. The main missing piece is guidance on the expected_revision parameter and on the tool's destructive potential.

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 does for two of three parameters, explaining the run value's nested string-vs-[name, args] form with a concrete example and defining search as a substring over names and descriptions. The expected_revision parameter is never mentioned, leaving one parameter fully undocumented.

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 ('Run any of Inkscape's ~1,070 actions, or search them') and explicitly splits the tool into two modes, run and search, so an agent knows the tool's scope immediately. It also names a sibling, export, as the tool for file writing.

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 real prerequisites ('Most act on the current selection; use selection(set_ids=…) first') and a clear alternative ('To write files, prefer export'). It does not, however, explain when to prefer this generic tool over the many overlapping siblings (align, distribute, style, attributes), which is a meaningful omission for an escape-hatch tool.

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