preflight

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

With no annotations provided, the description carries the full burden and delivers richly: rules are deterministic ('no judgement of yours involved'), the scope includes edits not yet saved, and it 'says nothing when nothing is wrong' — a non-obvious silent-success behavior that prevents an agent from misreading empty output as a failure. It also discloses that findings carry their source settings and explicitly denies any plate-model knowledge.

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?

Three tight paragraphs with distinct jobs: what it does, when to run it and why, then behavioral caveats. The core action is front-loaded in the first sentence, and every sentence carries non-redundant information without padding.

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 zero-parameter, no-annotation, no-output-schema tool, the description covers nearly everything: implicit inputs, timing, result semantics (silence vs. findings), and its boundary with measure_slice. The one small gap is the exact structural shape of a returned 'finding' beyond 'carries the settings it came from,' which no output schema exists to compensate for.

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?

There are zero parameters, so the baseline is 4. The description adds meaning beyond the empty schema by clarifying the implicit input: 'deterministic rules over the selected presets, including edits not yet saved' — this answers how a no-argument tool knows what to check. Since there is no parameter syntax to elaborate on, 4 is the natural ceiling.

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+resource: 'Check the settings in force against known-bad combinations.' It distinguishes itself from siblings by explicitly carving out measure_slice's domain ('overhangs, size and adhesion area' are not this tool's job) and by positioning its findings as inputs to describe_setting, which separates it from that sibling tool.

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 explicit when-to-use guidance: 'Run this before advising on a print, and before answering a general "what should I change".' It names the alternative for plate-geometry concerns (measure_slice) and explains why this tool takes priority — findings are facts 'worth saying first.' No timing or routing decision is left to inference.

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