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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds genuinely useful behavioral context beyond that: output is LLM-generated prose rather than rule-engine output, which tells the agent to expect non-deterministic, non-validated steps. It does not mention any accuracy/labeling caveats for lab use, which would have made it a 5.

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?

Front-loading with USE WHEN / RETURNS tags is scannable, but the definition wastes space on a redundant bilingual title repeat and an eight-item alias list that is keyword padding rather than guidance. It is functional but not tight.

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 2-parameter generation tool with annotations and no output schema, the description covers what it does, when to call it, and roughly what comes back (分步实验协议). The real gap is that sibling design_protocol_generate is never addressed, leaving the agent to guess between two visibly similar generators.

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 both query and sample_type are already documented with examples, and the description adds no format, constraint, or syntax guidance beyond echoing assay names. Baseline 3 is the correct landing point when the schema carries the parameter burden.

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?

Names a specific verb+resource: AI generation of a step-by-step bench protocol, with concrete assay examples (qPCR / WB / ELISA). It even adds a key qualifier ("AI-generated text, not a rule engine"). It stops short of naming the closely-related sibling design_protocol_generate, so the agent must still infer the boundary.

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?

"USE WHEN: the user needs a step-by-step bench protocol they can actually follow" gives a clear triggering condition plus intent language ("actually follow") that separates it from a design/planning tool. No explicit when-not or named alternative, so the exclusion side 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.