Run any Hermoso tool by name

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

Beyond the annotations, the description discloses that invoking through call_tool uses the same permissions, account, and result as a direct call; that arguments are validated against the target tool's schema; that invalid arguments return the expected parameters rather than silently defaulting; and that tools requiring unavailable connectors or withheld by host policy are refused by name with an actionable way out. This is rich, non-obvious behavioral context.

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?

Every sentence earns its place: purpose, source of parameter values, host-specific rationale, validation behavior, and refusal conditions. The most important action and scope are front-loaded, and the length is justified by the complexity and risk of a generic tool dispatcher.

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?

Given the tool's complexity as a dynamic dispatcher and the absence of an output schema, the description fully covers how to invoke it, how to source parameters, what validation behavior to expect, and when/why it may refuse. The statement that results match a direct call also informs the agent about return behavior without needing an output schema.

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. The description adds operational meaning by directing the agent to obtain the exact name and args from find_tools and by explaining that args must match the target tool's own schema, with validation errors surfacing expected parameters. This goes slightly beyond the schema's bare definitions.

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 opens with a specific verb and resource: 'Run ANY Hermoso tool by name', and immediately clarifies its unique scope—it can invoke tools not in the session's starting list, including paid-campaign, analytics, and channel-admin tools. This clearly distinguishes it from the many specific sibling tools and from enable_tools.

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 description gives explicit when-to-use guidance: it is the route on hosts like claude.ai and ChatGPT that cannot reload their tool list mid-conversation. It also names the alternative (enable_tools) and explains why that alternative fails on such hosts, plus instructs the agent to get the exact name and args from find_tools first.

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