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

With no annotations, the description does real work: it discloses that file metadata wins over the `experiment` argument and that a contradicting value surfaces in `experiment_warning` rather than being honored. It stops short of covering file-format support, failure modes for unreadable spectra, or what a truncated `max_crosspeaks` result looks like.

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?

Three tight paragraphs: what it does and returns, then argument-precedence rules, then routing to a sibling. No filler, and the core purpose is front-loaded in the first line.

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 like `experiment_warning` needn't be detailed further, and the description covers the main behavioral surprises for a read-only analysis call. Minor gaps remain around accepted file formats and the meaning of the crosspeak cap, but nothing that would cause a wrong 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% across 4 parameters, so the description must compensate; it fully explains the trickiest one (`experiment`) including override semantics. But `path`, `api_key`, and especially `max_crosspeaks` (default 200, implying result truncation) get no explanation at all, leaving the practical impact of that cap invisible.

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 and resource ('Analyze one 2D NMR experiment') plus the expected output ('crosspeaks and the correlations they imply'), and enumerates the supported experiment types (HSQC/HMBC/COSY/NOESY/TOCSY/ROESY). This lets an agent distinguish it from 1D siblings like covnmr_analyze and from assignment-oriented tools like covnmr_sudoku.

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?

Explicit conditional guidance: pass `experiment` only when the file's pulse sequence records none. It also names the alternative path — hand 2D files to covnmr_sudoku for atom-by-atom assignment — which is a clear use-vs-use-else rule.

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