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

The annotations only tell the agent this is a non-destructive write; the description adds real operational detail the annotations cannot: every enzyme name is validated against the cut catalog, an unknown name aborts the entire save (atomic, name-identified failure) rather than silently dropping members, and an existing collection is protected unless replace is set. No contradiction with destructiveHint=false, since overwrite is explicitly opt-in.

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?

Purpose is front-loaded in the first sentence, and the validation and overwrite guarantees follow in order of importance. The middle sentence carries a small editorial aside ('a collection that silently lost two enzymes is worse than one that was never made') that is persuasive rather than strictly necessary.

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 an output schema present and full param coverage, the description need not explain returns. For a write tool it covers the important behavioral guarantees (validation, atomic failure, opt-in overwrite) but says nothing about permissions or the activate/default-active behavior context, leaving minor gaps.

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 the baseline is 3. The description frames why names must be engine-resolved and reiterates the replace protection, but adds little syntax or format detail beyond what the schema properties already state.

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 states a specific verb and resource: save a set of enzymes as a named collection in the Enzyme Collections panel. It also ties the purpose to a concrete workflow (a scan that produced enzymes worth keeping), which distinguishes it from read-side siblings like enzyme_collection without needing to name them.

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 a clear usage context — use it after a scan to persist the enzymes worth keeping rather than retyping the list — and the param notes reinforce wiring names from enzyme_cut_counts, digest_fragments or enzyme_collection. It stops short of explicit exclusions or a named alternative for the opposite case, so no 5.

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