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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered; the description adds genuinely new context: the multi-source registry scope, AND semantics for filters, and the exact return envelope { offerings, total, counts }. It stops short of stating pagination or rate-limit behavior, which is why it is not a 5.

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 purpose and source scope, then the return shape, then sibling routing — a sensible priority order. It is dense but nearly every clause earns its place; the parenthetical source list and the return-field enumeration are the only slightly heavy stretches.

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 17-parameter, zero-required-parameter tool with no output schema, the description does the important compensating work: it enumerates the return fields (pricing, trust tier, capabilities, probe results, rank explanation) and states totals/counts. Per-parameter meanings are left entirely to a very thorough schema, which is acceptable here but keeps it short of a 5.

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 coverage is 100%, so the schema carries parameter detail and 3 is the baseline. The description still adds meaning beyond it by declaring that optional filters combine with AND and by explaining that `limit` truncates results while `total` still reflects every match — a cross-parameter behavior the schema cannot express.

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 and resource ("Search AI inference offerings") and immediately scopes it to two source classes: registered nodes AND imported catalogs (OpenRouter, Hugging Face, models.dev, local nodes). It also names the two sibling tools that serve different intents, so an agent can tell search from get_offering and recommend without opening a schema.

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?

Gives explicit routing ("Use get_offering for one offering's full card, recommend to let the advisor choose") and states the filter combinatorics ("All filters are optional and combine with AND"). It lacks an explicit when-not statement such as how it relates to find_locations/find_residency for pure geography questions, but the core selection guidance is clear.

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