inspect_slice

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

Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint=false, so the description's job is to add context — and it does: it discloses that G-code is never executed, that compact mode keeps counts/shared path totals/bead-edge margins while raw paths land at report_path, and it explicitly bounds what the output means (unknown firmware/plate origins/extruder mappings stay unknown; targets do not establish actual temperatures or physical fusion). These epistemic caveats are exactly the kind of behavior an agent cannot get from structured fields.

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?

The purpose is front-loaded in sentence one, followed by the selection rule and then output caveats — a sensible order with no filler. It is dense and jargon-heavy ('bead-edge margins', 'shared path totals'), but each sentence conveys distinct information.

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?

With no output schema, the description must explain return shape, and it does so partially (compact vs raw, report_path). Gaps remain around the unexplained revision parameter and what happens when job_id is absent or the revision is not succeeded, which matters for a tool whose behavior branches on those inputs.

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% for three parameters, so the description must carry the load. It explains job_id (inspect that exact succeeded revision, implying a succeeded-job precondition) and project_id (the saved project fallback), but the 'revision' parameter is never mentioned, leaving one of three parameters with no semantics anywhere.

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 first sentence names a specific verb and specific resources: 'Inspect embedded G-code targets, object layers and feature feeds without running it.' The read-only framing ('without running it') separates it from execution tools like start_slice, though it does not explicitly distinguish itself from close siblings such as analyze_geometry or inspect_project.

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?

It gives one concrete routing rule: use job_id to inspect that exact succeeded revision, otherwise inspect the saved project including older sliced imports. That is guidance about parameter selection rather than tool selection — there is no statement of when to choose this over analyze_geometry, compare_candidates, or inspect_project.

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