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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds domain behavior beyond that (one oligo per site, a shared annealing reaction, synonymous codons drawn from a usage table), but says nothing about how required inputs interact, what a partial design looks like, or the degenerate-codon collapsing that materially changes the output.

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 dense sentence, front-loaded with the tool's identity and mechanism, with no filler. It could be split for readability but every clause carries information.

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?

An output schema exists and the input schema is fully annotated, so the description needn't restate parameters or return values. For a 39-parameter design tool, however, it gives no orientation to the scoring/tradeoff machinery or to the record-passing inputs, leaving the agent to read the schema cold.

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 every one of the 39 parameters, including the 'Advanced' tuning knobs, is already documented in the schema; baseline is 3. The description adds marginal meaning by tying `organism` to the codon draw and implying that multiple substitutions at one position form a single site, but nothing about the scoring weights or flank parameters 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 names a specific verb (Design) plus a specific resource (QCLM multi-site oligos) and pins down the mechanism: one primer per mutated site, all annealing in one reaction, codons drawn from an organism's usage table. It is clear what the tool produces, though it never names the siblings it supersedes (design_mutagenesis_primers, design_saturation_primers), so sibling differentiation is left to the agent.

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 'multi-site' framing implies when the tool applies (several mutations designed to anneal simultaneously), but there is no explicit when-to-use vs when-not statement and no pointer to the single-site or saturation alternatives. Usage is inferable from the domain language rather than stated.

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