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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the agent knows this is a safe deterministic calculation. The description adds real value beyond that by disclosing the model's fidelity boundaries — that results rest on G.652.D attenuation maxima and deliberately omit chirp, PMD, nonlinearities, overload and compensation — which tells the agent these are engineering estimates rather than full-fidelity simulations. No cost, rate-limit or error behaviour is mentioned, but none is plausible for a pure calculator.

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?

Two sentences, roughly forty words, with the primary computation front-loaded and the model boundaries second. Nothing is redundant and no filler is present.

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?

With 12 required parameters and no output schema, the description usefully names the returned quantities, so the agent knows what comes back. It also scopes the physics the model covers. The remaining gap is that units and the role of the optional power_mw parameter are left entirely to the schema, and the notion of 'reach' (presumably km) is never defined.

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 100% and the schema already labels linewidth_nm and bit_fraction as assumptions and connector_db/splice_db as user specifications. The description restates that spectral width and bit-period fraction are explicit assumptions, which reinforces the schema but adds no new meaning, and it never mentions the optional power_mw parameter. Baseline of 3 is appropriate when the schema does the heavy lifting.

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 description names exactly what is computed (power margin and fixed-component power reach), the physical model basis (ITU-T G.652.D cable attenuation maxima), and the secondary outputs (chromatic broadening, dispersion-limited estimate). No sibling tool touches optical link budgeting, so it is trivially distinguishable from the rest of the catalogue.

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?

Usage is only implied: an agent can infer this is the tool for optical fibre power-budget questions, but the description never states the triggering context (e.g. 'use when checking whether a fibre span closes'). It does provide a partial when-not through the explicit exclusion list (chirp, PMD, nonlinearities, overload, compensation), which tells the agent when the answer will be wrong, but no alternative tool or method is named.

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