Provider Health & Schema Drift

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

With no annotations supplied, the description discloses live upstream probing, cached verdict reuse, forced re-probing, and warning propagation to other tools. It also defines the provider states and degradation fields, though it does not mention operational implications of forced refresh such as additional latency or upstream load.

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 purpose is front-loaded, followed by caching behavior and compact, scannable Args and Returns sections. The refresh semantics are repeated, and the Returns discussion is not strictly necessary given the output schema, making the description slightly more verbose than required.

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 one-parameter health probe with an output schema, the description supplies the invocation behavior, cache model, downstream consumers, and status vocabulary needed to call it correctly. Not naming the two providers is a small contextual omission, but it does not prevent correct selection or 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?

Although schema description coverage is 0%, the description fully compensates for the sole parameter: ``refresh=True`` forces fresh probes, while the default path reuses the cached verdict for the configured TTL. The inline explanation and Args entry make the boolean's operational effect unambiguous.

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 opening line uses specific verbs, “Probe” and “report,” and identifies the resource as both provider upstreams and their API schema drift. Explaining that every other tool consumes this monitor's cached verdict clearly distinguishes it from the market-data and analysis siblings.

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 explicitly says to use ``refresh=True`` for an immediate re-probe and explains that other invocations reuse the cache for ``TAPEBASIS_HEALTH_TTL`` seconds. It also describes how siblings consume the verdict, but does not give a broader decision rule for when to run this monitor directly versus relying on their warnings.

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