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

With annotations already declaring readOnlyHint=true and idempotentHint=true, the description adds genuinely valuable behavioral context: outcomes are 'ranked by how few independent mis-ligations each needs,' cross-talk data is explicitly attributed (Potapov/Pryor ligation data), and the limitation is honestly disclosed ('Reports no probability per outcome: the ligation data does not measure transformation or vector background'). This is exactly the kind of caveat-dense behavioral disclosure the annotations can't express.

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 opening sentence is information-dense and slightly run-on (though it earns its length by cataloguing failure modes), and the middle sentences are efficient. It's front-loaded with the core purpose and ends with an honest limitation. Minor wordiness like 'the backbone self-circularised' adds color but is justifiable for a molecular biology audience. No waste, but a touch over-long.

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 the complexity — 8 parameters, no output schema, two assembly methods, two datasets, and a nuanced cross-talk annotation system — the description is remarkably complete. It explains the ranking principle, data provenance, method-specific behavior, downstream tool integration, and important limitations. The lack of an output schema raises the burden on this description to characterize return behavior (ranked full sequences), which it does well.

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% with rich detail: enums for method and dataset, defaults documented, cross-tool references ('the same list cloning_simulate takes'), and contextual flags like 'Golden Gate only' and 'Gibson only.' The description adds no parameter-specific semantics not already in the schema, so the baseline of 3 for high-coverage schemas is appropriate.

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 description pairs a specific verb ('Enumerate') with a precisely-scoped resource ('the specific wrong plasmids a multi-part Golden Gate or Gibson assembly can produce') and catalogs what that entails (dropped, inverted, duplicated, swapped parts; backbone self-circularised). It clearly differentiates from siblings like cloning_simulate (generates intended assemblies) and verify_assembly, while the output direction toward diagnostic_digest disambiguates it from that 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?

The description gives clear workflow guidance ('Feed the result to diagnostic_digest to pick a screening enzyme') and realistic exclusions ('Reports no probability per outcome'), implying when the tool is insufficient. However, it never explicitly names the obvious sibling alternative (cloning_simulate) for the 'intended assembly' case — it says 'the same list cloning_simulate takes' but doesn't say 'if you want the correct plasmid, use X instead.' A named alternative would push this to 5.

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