science.stoichiometry

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

Annotations already cover safety (readOnly, closed-world, idempotent), and the description adds genuinely new behavioral context: numeric values are Decimal strings, no rounding is applied, atomic weights match molar_mass, and unbalanced coefficients silently produce wrong results. That last point is a valuable failure-mode disclosure not derivable from annotations.

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?

Four sentences, front-loaded with the purpose, then input shapes, then behavioral caveats. Dense but every sentence carries information; no filler.

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 needn't be explained. Given 0% schema coverage and nested objects, the description supplies enough input structure and caveats for correct invocation; only edge-case handling of overlapping mass/moles inputs is left unaddressed.

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 0% and the schema is loose (additionalProperties true, no per-property docs), so the description must compensate — and it does, spelling out the shape of reactants ({formula, mass(g) or moles}), products ({formula}), and coefficients ({formula: integer}), plus the Decimal-string convention. Minor gap: it doesn't say what happens if both mass and moles are supplied for one reactant.

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?

States a specific verb+resource: find the limiting reactant from balanced coefficients and compute moles and mass for each substance. It also distinguishes itself from the molar_mass sibling by declaring it uses the same atomic weights, so an agent can tell it apart without opening either schema.

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?

Gives clear preconditions (coefficients must already be balanced or results are wrong) and explicit exclusions (yield and impurities are not reflected), which tells the agent when not to rely on it. It stops short of naming an alternative tool to use for yield/impurity problems.

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