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

Annotations already declare this a safe, closed-world read, so the description's job is to add substance, which it does by disclosing exactly what computation runs: geNorm pairwise variation M, NormFinder intra/inter-group variance, BestKeeper SD of raw Cq with index correlation, and comparative delta-Ct, all under RefFinder consensus. That tells the agent what conclusions the output can support. It does not discuss result shape or failure modes, though an output schema presumably covers returns.

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?

A single front-loaded sentence that leads with the question answered and then substantiates it with the four methods. The parenthetical method glosses are efficient rather than padding, though the sentence is long and the method abbreviations slightly crowd the algorithm names.

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 read-only ranking tool with a fully described schema, rich annotations, and an output schema, the description carries what the structured fields cannot: which algorithms are combined and on what basis each judges stability. Nothing an agent needs to select or call this tool correctly is missing.

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% and the cq_table and normfinder_arm parameters are documented in depth in the schema itself, including the Group-column dependency, so the baseline is 3. The description's mention of the four algorithms gives useful background for interpreting the normfinder_arm choice but adds no direct constraint or format detail beyond what the schema states.

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 opens with a precise framing of the question the tool answers ("Which candidate reference gene is actually stable") and enumerates the four ranking algorithms plus the RefFinder consensus, so the resource and operation are unmistakable. It stops short of naming a sibling it is not, which keeps it from a 5 given siblings like discover_reference_stability and discover_reference_concordance exist.

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?

Usage is implied rather than stated: the agent can infer this is the tool for choosing among candidate reference genes from a Cq table, and the schema reinforces the input shape. There is no explicit when-to-use, when-not-to-use, or routing note pointing at discover_reference_stability versus this tool, so the agent must infer the boundary from the names alone.

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