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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety bar is low; the description still adds value by disclosing the response envelope (primary result, step summary, warnings, safety notes). It also discloses mode-conditional input expectations, which matters more than the annotation set here. It omits computational caveats (rounding, unit-conversion assumptions).

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-loaded with 'Use when', then mode semantics, then return contents — a clean trigger-to-behavior progression. Every clause carries information: the parenthetical examples are user-language triggers, and the mode breakdowns are not restated elsewhere in prose.

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, so return values need not be explained, yet the description still summarizes them. For a 13-parameter conditional allOf/oneOf schema, the mode + solveFor narrative gives enough scaffolding to construct a valid call. The one gap is that it does not state that solid mode requires molecularWeight and the unit parameters, leaving that inference to the schema.

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 coverage is 69% across 13 parameters, so baseline would be 3. The description compensates by explaining what each mode consumes (solid: molecular weight, target concentration, final volume; stock: the four solvable C1V1 variables), which maps the conditional schema onto a mental model. It does not clarify unit parameters or the optional solvent/solutionName fields.

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 two concrete computations — solid mass from molecular weight/target concentration/final volume, and C1V1 dilution — with the C1V1 formula spelled out. It is specific enough that an agent knows exactly what class of answer comes back. It does not, however, name any sibling (serial_dilution, lnp_formulation) to disambiguate similar wet-lab math.

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 opening clause is a trigger phrase tied to real user phrasing ('how many grams for X mM in Y mL, making up a buffer or salt solution'), which is genuinely useful routing. It gives clear positive conditions but never states when NOT to use it or which sibling to pick instead for stepwise dilution series.

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