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

Annotations already include readOnlyHint=true, and the description reinforces this by describing the tool as a discovery step that returns data. It adds valuable behavior not in annotations: that sub_domain is the primary routing key, params must be passed via sub_domain_params, and required params must be passed as empty strings. However, destructiveHint=true is not addressed, which could confuse an agent; the description could have explicitly stated it is non-destructive.

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?

Although lengthy, the description is well-structured with sections, bullet lists, and bolded emphasis. Every section adds necessary information (when to call, domain list, return format, critical usage rules). No filler or redundancy; it uses visual cues to prioritize key behavioral instructions.

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 no output schema, the description fully compensates by explaining the return format (markdown table) and exactly how to consume the results (pass sub_domain to search, use sub_domain_params, handle required params). It also covers edge cases like multi-domain queries and required-mandatory parameters, making it self-sufficient for correct tool use.

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% with both parameters described, but the description goes far beyond the schema. For domains, it clarifies batch semantics (max 5, takes priority over domain), provides examples of combining domains, and advises using plural when uncertain. This deep semantic guidance is critical for correct invocation.

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 identifies the tool as Anysearch's domain discovery tool and step 1 of vertical search, explicitly stating it returns valid sub_domains and sub_domain_params. It distinguishes from siblings by positioning itself as a prerequisite to search, making its role distinct from batch_search, extract, and search.

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?

This is exemplary. It states exactly when to call (before any search using a domain), provides a list of domains to choose from, includes concrete examples, and gives clear directives such as 'ALWAYS prefer the domains (plural) parameter' and 'use batch_search when multiple sub_domains returned', thereby guiding tool selection and execution.

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