Turn on more Hermoso tools

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

Annotations already include idempotentHint=true, destructiveHint=false, and readOnlyHint=false, but the description adds valuable behavioral context: how the tool behaves on different host types (stdio/CLI re-read vs. chat fixed roster), that it explicitly reports the limitation rather than false success, and that it never turns anything off and is free/instant. It also explains why ads/analytics are excluded by default (size), which is beyond what annotations could convey.

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 description is lengthy but remarkably dense—every sentence contributes critical information. It front-loads the core purpose, then covers caveats, triggers, and technical details in a logical order. No filler or redundancy; the length is justified by the tool's meta-nature and the need to explain both host behavior and usage triggers.

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 this is a tool-enabling tool with only one parameter, the description is exceptionally complete. It explains the full context: why certain groups are excluded by default (size), when to invoke it, how it differs from connect-time configuration, and what to expect in response. An agent has everything needed to correctly decide when and how to call it.

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% (the only param `groups` has a description), but the description adds far more: it lists all valid group names, gives usage examples with `['ads']` and `['analytics']`, clarifies that unknown names are refused by name, and explains the default exclusions. This goes well beyond schema to fully define the parameter's meaning and accepted values.

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 clearly states the tool's purpose: 'Switch on a group of tools that is not in this session's roster.' This is a specific verb and resource, and it distinguishes this meta-tool from the many sibling tools that perform content operations. The detailed explanation of how it differs from a connect-time configuration (e.g., `?tools=all`) further clarifies its unique role.

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 provides explicit when-to-use guidance with concrete examples: 'CALL THIS THE MOMENT YOU NEED ONE' and specific triggers like 'If the user asks to build...an ad campaign, call enable_tools({groups:['ads']}) first.' It also explains when not to rely on it (hosts that don't re-read the tool list) and points to the reliable alternative (`?tools=all`). This is model guidance.

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