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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety bar is lower, yet the description goes further: it discloses cache TTLs (300 s public, 24 h for selected stable reference tools), that stale results are marked, and that credentials are never forwarded and nothing is published. These are concrete behavioral traits not derivable from annotations. Only the return shape and failure behavior remain unstated.

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?

Four short clauses, front-loaded with the core action before the caching and security details. Nothing is wasted, though the telegrams-style compression trades some clarity for brevity. Efficient overall.

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?

This is a high-complexity meta-tool with a nested free-form arguments object, an opaque provider_id/tool_name pair, 0% schema coverage, and no output schema. The description omits how to discover providers/tools, what the arguments object contains, and what a call returns or how errors surface. It is materially under-complete for the tool's complexity.

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 0% across four parameters, so the description must compensate and largely does not. "With its exact schema" hints that arguments must conform to the target tool's signature, but provider_id, tool_name, and api_key receive no explanation anywhere. The one hint it provides is useful but far short of what is needed for a dispatcher.

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?

"Call a reviewed read tool with its exact schema" gives a verb (call) and a fuzzy resource (a reviewed read tool), which is only partially interpretable without knowing what provider tools are. It does not distinguish itself from siblings like list_provider_tools or list_research_connectors, which are the natural discovery counterparts. The purpose is implied but not sharply defined.

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 only usage-adjacent line is "Check original sources," which is a caution rather than a when-to-use rule. There is no mention of how to obtain provider_id/tool_name (e.g., via list_provider_tools) or when this dispatcher should be preferred over the direct sibling tools. No exclusions or alternatives are named.

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