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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds useful behavioral detail beyond annotations: exact tool-name queries return full schemas and examples, and every response includes a top-level connectors array listing connected SaaS accounts. This helps the agent know what to expect from the response.

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 front-loaded with its core purpose and then provides compact, useful sections: examples, the call flow, connectors behavior, and categories. It is slightly longer than necessary because the category list duplicates the schema enum, but every other sentence earns its place.

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 there is no output schema, the description covers the important return behavior: tool+skill results, exact-name schema retrieval, and the connectors array. It does not detail the exact structure of the standard tool-results list, but it provides enough for an agent to use discover effectively.

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 schema already documents query and category. The description adds semantic value by showing how to use the query parameter: plain-language requests, categories, '*', or exact tool names like 'seo'. It also lists the category values in prose, reinforcing the enum meaning.

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 uses a specific verb ('Find') with a clear resource ('the right ToolRouter tool for your task'), and includes concrete examples like 'analyze a website' and 'check DNS records'. It also distinguishes itself from the use_tool sibling by laying out the discovery flow, so an agent can tell it apart from invocation 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 explicitly explains when to use discover: when you need to find the right tool, whether via plain-language task description, category, or exact tool name. It also names the downstream alternative, use_tool, in the flow 'discover → pick a tool + skill from results → call use_tool', and gives context on using the connectors array to pick the right account.

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