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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine behavioral context beyond that: output is 'pandas-compatible CSV', the report is composed of named artifacts, and the errors spreadsheet is characterized as the most useful output for a failed run. It does not spell out return structure, but an output schema exists.

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 sentences, front-loaded with the core action and then the wiring instruction; every clause carries information (report contents, output format, upstream inputs). It is dense but not padded. Minor density from the enumerated artifacts keeps it just short of ideal.

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?

Given a rich 7-parameter schema at 100% coverage, existing annotations, and an output schema, the description supplies the missing cross-tool wiring and format notes an agent needs to call it correctly. Nothing critical is absent, though a brief note on ordering (assemble first, then build report) would make it fully self-contained.

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 100%, so baseline is 3; the description adds value by tying parameters to report semantics (the enzyme becomes the report's `enzymes` column and should be left empty for Gibson to avoid implying an enzyme exists) and by specifying the required shape of `products` (id, sequence, fragmentNames). This is meaning beyond the schema, though not exhaustive for every parameter.

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 ('Build DnaCauldron's assembly report from an assembly result') and enumerates exactly what the report contains: the per-construct summary table, the constructs and errors spreadsheets as pandas-compatible CSV, and the Outcome / Number of assemblies stats. It also names the upstream assembly nodes it consumes, so an agent can distinguish it from unrelated report/export siblings.

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?

The second sentence gives explicit wiring context: 'Wire golden_gate_assemble or gibson_assemble's products, errors and warnings outputs into it', which tells the agent when this tool is appropriate (after an assembly run) and which sibling outputs feed it. It stops short of stating exclusions (e.g. when a report is unnecessary), so it is clear context rather than full when/when-not guidance.

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