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

With no annotations, the description carries the full burden and does well: it discloses that the two modes return different key sets and that `mode` disambiguates, and it warns that `atom_attribution` is a nearest neighbour, not an assignment, and will name an atom even when nothing is within tolerance. It omits whether the call is read-only/costly and that an `api_key` may be required.

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-line purpose, then organised under explicit mode headings with the caveat paragraph last. Dense but every paragraph maps to a distinct decision the caller must make; only the attribution paragraph runs slightly long for the value it adds.

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 enumerated, yet the description still names the key that carries the answer and flags the mode-dependent key set — the piece an agent cannot infer. With 9 parameters and no annotation coverage, the only real gaps are the undocumented `solvent` and `api_key` inputs.

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%, so the description must compensate, and it does for most parameters: `ppm`, `multiplicity` ("t", "dd"), `j_values` (comma-separated Hz with an example), `nucleus` (default 1H), `c_ppm`, `experiment` (HSQC/HMBC/COSY) and `smiles` all get meaning beyond their bare types. It leaves `solvent` (default CDCl3) and `api_key` entirely undocumented.

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?

Opens with a specific verb+resource framed as a question the tool answers ("Interpret ONE peak, or one 2D crosspeak: what is this signal?") and names the output key holding the answer. It then splits the tool into two clearly named modes, so an agent can tell exactly which capability it is invoking, distinct from siblings like covnmr_analyze or covnmr_2d_analyze.

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?

Mode selection is explicit: peak mode is the default, and correlation mode requires `c_ppm` AND `experiment`. It also routes the adjacent task away ("For a full assignment use covnmr_verify or covnmr_sudoku"). What's missing is guidance on when to reach for this tool versus the broader covnmr_analyze / covnmr_2d_analyze siblings.

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