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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), and the description adds context beyond them: the search spans tools outside the session's starting list, it is free, and it returns one-line parameter summaries. These traits align with the annotations, so there is no contradiction.

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 sentences and roughly 90 words, with the core purpose front-loaded and every sentence carrying distinct information: scope, trigger, decision rule, follow-up, and cost. It is dense, but appropriately so for a discovery tool that must override the agent's default assumption that its list is complete.

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?

With no output schema, the description carries the burden of explaining return values, and it does ('parameters in one line'). For a discovery tool with zero required parameters, it covers scope, when-to-use, output shape, follow-up action, and cost; limit defaults and enum values live in the schema where they belong.

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%, putting the baseline at 3, but the description adds value by showing query formulation examples ('lead form', 'whatsapp', 'google ads keyword', 'meta insights') and naming concrete group values (`ads`, `analytics`, `channel_admin`) that map directly to the group parameter.

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 sentence states a specific verb+resource ('Search EVERY Hermoso tool'), names the three search dimensions (name, task, group), and specifies the output ('each one's parameters in one line'). It clearly distinguishes itself from siblings like call_tool and hermoso_capabilities by explicitly flagging the hidden `ads`, `analytics`, and `channel_admin` groups.

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 an explicit trigger ('Use it the moment the user asks for something you do not see a tool for') with concrete examples (campaign, ad set, lead form, click-to-WhatsApp ad). It reinforces the decision rule with a strong negative framing ('a tool missing from your list is NEVER proof the feature is missing') and names the follow-up action ('Then run the tool with call_tool'), effectively drawing the boundary against execution tools.

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