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

With readOnlyHint and idempotentHint already present, the description adds non-obvious behavior: it 'never reads or writes planner workspaces', only returns catalog data and public URLs, and offers a specific retry policy for transient transport errors. This goes beyond the annotations and helps an agent reason about safety and repeatability, even if it doesn't mention rate limits or authentication.

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 description is only a few sentences but carries purpose, usage context, behavioral constraints, and retry handling. There is no redundancy or filler, and the most important statement ('Search public fiber catalog rows') is front-loaded.

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?

For a simple read-only search tool with a rich input schema and an output schema present, the description covers the core usage, behavioral scope, and retry procedures. It could elaborate on result set handling or when not to use it, but those are not critical gaps given the structured schema and the search-based context.

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?

The schema already documents all three parameters (coverage 100%), so the baseline is 3. The description enriches the query intent by naming fiber attributes and the wavelength use case, but it does not add concrete parameter-level details beyond the schema. It relies on the schema's own parameter descriptions, which are already good.

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 clearly states the tool's purpose with a specific verb+resource: 'Search public fiber catalog rows'. It enumerates the fiber attributes it is appropriate for (part numbers, mode-field diameter, numerical aperture, wavelength compatibility), which mainly distinguishes it from lens/collimator tools. However, it does not explicitly mention or contrast with sibling tools, so cross-tool differentiation is left to inference.

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 says 'Use when the user asks for ...', which is direct and explicit. But it lacks an explicit 'don't use when' section and does not point the agent to one of the siblings like search_fiber_collimators or search_lenses. The retry guidance is useful, though it's about invocation behavior rather than alternative selection.

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