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 safety profile is covered structurally. The description still adds real value beyond them by asserting cost behavior twice ('FREE', 'nothing here spends') and clarifying that quoted prices are live upstream registry amounts rather than estimates — the key thing an agent needs before deciding whether searching is a commitment.

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?

Three compact sentences with the highest-value fact ('FREE') front-loaded and the workflow hint second. Slightly dense with domain jargon ('SML paid routes', 'capsules'), but every clause carries information an agent needs to select and use the tool.

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 two-parameter, zero-required, read-only search tool with no output schema, the description covers what it returns in useful terms (routes with live prices, plus capsules), the cost model, and the downstream step. Nothing material is missing for correct invocation.

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%, so both `query` (with examples) and `limit` (1–50, default 20) are already documented, making 3 the baseline. The description adds context that results are 'capped' and shows the payload shape a route is called with (query|path|body), which indirectly hints at what to search for, but it adds nothing about how `limit` or query matching behaves.

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 states a specific verb and resource ('Runtime catalog search') and enumerates exactly what it returns: SML paid routes callable via sml.call(id, {...}) with live per-call USDC prices, plus published capsules. It also names the sibling it feeds into (omnigate_runtime_execute), so an agent can separate it from the other catalog/discovery tools 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?

Explicit sequencing is given: 'Use this before omnigate_runtime_execute to pick route ids,' which tells the agent when to reach for it and what it feeds. There is no when-not guidance and no mention of sml_discover, the closest sibling that presumably also surfaces routes, so the agent must infer the boundary itself.

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