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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add computational behavior. It does so usefully: it discloses the source model, that results are derived from the Gaussian model (Gouy phase), and critically that phase and intensity for M^2 > 1 are Gaussian estimates rather than exact — an accuracy caveat an agent needs when interpreting results. It stops short of noting edge-case behavior such as degenerate or zero inputs.

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?

A single dense sentence, front-loaded with what is computed and the model source, followed by the returned quantities and the M^2 caveat. Every clause carries information; the output list is a long enumeration but substitutes for a missing output schema, so it earns its space.

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 no output schema, the description compensates by enumerating the returned quantities, which is the right move for a pure calculator. However, for a tool with seven mandatory parameters it leaves notable gaps: no statement of whether focal_mm may be zero to skip the lens, no sign convention for z relative to the waist, and no units expectations beyond those in the schema. Adequate but not complete for calling the tool confidently on edge cases.

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% with seven simple documented parameters, so the schema carries the semantics and a baseline 3 is appropriate. The description loosely maps inputs to outputs (focusing relates to focal length and lens radius; M^2 relates to the ISO ratio), but adds no unit conventions, sign conventions for z, or guidance on special values such as focal_mm = 0 meaning 'no lens' — which matters because all seven parameters are required.

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 computation ('Gaussian propagation and thin-lens focusing') plus its theoretical basis (Siegman 1986, ISO 11146 M^2), so an agent knows exactly what physical quantity is being computed. It also enumerates the returned quantities, which further pins down scope. No sibling differentiation is offered, but the sibling list contains no other Gaussian-beam tool, so there is nothing to disambiguate against.

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?

There is no statement of when to call this versus alternatives (e.g., fibre_link_budget or detector_signal, which also touch beam/optical quantities) and no prerequisites such as the need for a waist radius and wavelength in consistent units. Usage is only implied by the physics vocabulary. The one adjacent signal is the M^2 > 1 accuracy caveat, which is a limitation rather than routing guidance.

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