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

With no annotations, the description carries the burden well: it discloses the full verdict vocabulary (pass/fail/incomplete/reference_not_found), the rule that an untested criterion can never yield pass, and the limit defaults (1.0 Hz, 250 S/N, 0.0 ppm reference). It does not state that this is a read-only analysis (no mutation, no data destruction) or anything about auth/api_key expectations, which leaves a small gap for a zero-annotation tool.

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?

The first sentence front-loads what is measured, followed by verdict semantics and defaults, so the important content is early. It is dense but nearly every sentence carries operational information; the regression note about absorbing covnmr_quality is mildly extraneous but brief.

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?

Because an output schema exists, the description needn't describe return structure, and its coverage of verdict logic, defaults, and conditional evaluation is enough for a 10-parameter tool. The gaps are the undocumented nucleus/solvent/api_key/path parameters and the absence of any read-only/mutation disclosure.

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%, so the description must supply parameter meaning, and it does for the domain-critical ones: min_sn (250), max_linewidth_hz (1.0), reference_peak_ppm (0.0, TMS), plus the conditional semantics of signal_ppm, field_mhz, and line_broadening_hz. However, four parameters — path, api_key, nucleus, and solvent (default CDCl3) — receive no explanation at all, leaving a material gap at 0% schema coverage.

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?

Names a specific standard (USP <761>) and the exact quantities measured: FWHM linewidth of the reference line, signal-to-noise, and peak asymmetry. It also explicitly distinguishes itself from a retired sibling (covnmr_quality), so an agent can place it among covnmr_method_validate and covnmr_verify without opening the 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?

It gives clear conditional guidance: S/N is only evaluated when `signal_ppm` is supplied, linewidth reflects the instrument unless `line_broadening_hz` is given, and the frequency comes from the file unless `field_mhz` is provided. What's missing is explicit routing against other nmr validation siblings (e.g., method_validate/verify), so it stops short of full alternative selection guidance.

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