predict_spectrum

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

With no annotations, the description carries the full burden and does: it discloses the method (curated table matched to structure, topological proton equivalence), the deliberate limitation (no ppm chemical shifts, deterministic rather than modeled), and the output ordering rule (high wavenumber first, centrality-ordered assignments). These are exactly the behavioral facts an agent needs to trust and interpret results.

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 the one-sentence purpose, then structured bullets mapping topic to question, then constraints, then exclusions — a sensible order. A few phrases ('all of them exam material', 'honestly limited') are tone rather than information and could be trimmed without loss.

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?

Return values need not be explained since an output schema exists, and everything else an agent needs for a three-parameter prediction tool — topic routing, argument formats, determinism, known limitations, sibling routing — is present. Nothing material is missing for correct invocation.

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 0%, but the Args block compensates by documenting all three parameters: accepted name formats (English/IUPAC or SMILES) for structure, units (cm⁻¹) for wavenumber, and which topic consumes each. It stops just short of stating what happens if an inapplicable parameter is supplied (e.g. wavenumber with 'ir_bands'), leaving that edge case to inference.

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 opening line states a specific verb and resource ('say what a spectrum of this structure should show — or read a band') and the three topics are enumerated by name and output. The closing 'Not this tool for' paragraph explicitly separates it from generate_spectrum and lookup, so an agent can disambiguate without opening a 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?

Each topic carries its own use condition and required argument ('ir_bands' needs structure, 'assign_wavenumber' needs wavenumber in cm⁻¹). The alternatives — generate_spectrum for drawing from known peaks and lookup for measured data — are named with the condition that selects them, and the hand-off from band list to generate_spectrum is spelled out.

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