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

Annotations already say readOnly (consistent — routing does not mutate anything), and the description adds substantial context the annotations do not: it enumerates the full response payload (endpoint, input schema with example args, call hints, reliability verdict, price and payment method, ranked fallbacks) and explains that freeOnly/requireAutomatable/maxPricePerCall narrow the candidate set. It could go one step further on latency/caching behavior, but it already carries far more than its annotations.

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 the trigger conditions and then a compact payload description; both sentences earn their place. It is dense and slightly long for one paragraph, but there is no filler and the WHEN TO CALL / what-you-get / narrowing / supersedes order is logical.

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 tool with no output schema, the description must explain the return shape — and it does, itemizing every field of the routed result including fallbacks and pricing. Combined with the trigger conditions and parameter narrowing notes, an agent has everything needed to call and interpret it correctly.

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 baseline is 3, but the description adds value by grouping the constraint parameters into a single clause ('freeOnly / requireAutomatable / maxPricePerCall narrow the choice') and by tying requireAutomatable to the unattended-agent use case. It gives the agent a mental model of how 'task' vs. the filter parameters interact, which the schema alone does not.

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?

States a concrete action — resolve a plain-language task to a single best live tool with endpoint, schema, and fallbacks — which is clearly distinct from siblings like discover_tools or prepare_tool_call. It even names the four sibling tools it supersedes, so an agent can route unambiguously.

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?

Opens with an explicit 'WHEN TO CALL: first' plus three enumerated trigger conditions (missing capability, failing connected tool, user asking which tool to use). This is the strongest possible form of when-to-use guidance and leaves nothing to inference.

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