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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered without needing the description. The description adds useful context about the catalog being 'live' and what fields are returned, but it does not disclose pagination behavior, default result counts, or the fact that models without a chosen benchmark score sort last—the latter lives only in the sort parameter's schema description.

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 long but highly information-dense: the opening sentence states purpose, the middle sentence gives a strong usage directive, and the remaining text is a compact enumeration of search/sort and filter families. It avoids prose fluff, though the filter list could arguably defer more to the schema for exact option values.

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?

Given the tool's complexity, no output schema, and a single nested request object, the description reasonably covers the selection workflow and key return fields. It misses a few relevant details like limit/offset defaults and the distillable filter, but those are documented in the schema, so the description does enough to orient an agent toward correct usage.

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?

Even though the reported schema description coverage is 0%, the description substantially enriches the parameter semantics: it gives units ($/M), value ranges (0-1 for tool success rate), case-sensitivity for providers (e.g. Groq), and examples for filters. It also bundles related filters under 'Search/sort' and 'Filters,' making the request object's nested parameters far more interpretable than the raw schema alone.

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 opens with a specific verb and resource: 'List the live OpenRouter model catalog' and enumerates the returned data (pricing, context length, modalities, supported parameters, benchmark scores). It also states the intended goal—'to pick a model and wire the right slug into code'—which clearly distinguishes it from sibling tools like get-model or list-providers.

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?

The description gives actionable guidance: 'Prefer the server-side params over fetching the full list and post-processing,' which tells the agent to use this tool's sorting/filtering rather than fetching everything. It does not explicitly name sibling alternatives for narrow cases such as fetching a single model, but the directive is clear and contextually sufficient.

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