search_nodes

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

Annotations already declare readOnlyHint=true. Description adds behavioral details: case-insensitive substring matching, exact type matching, flat array return. No contradictions with annotations.

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?

Two sentences, no redundant words. Every sentence adds necessary information: what it does, constraints, scope, and return type.

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?

For a search tool with 3 parameters and no output schema, the description covers all essential aspects: search criteria, required input constraints, scope default, and return format. Adequate for an agent to invoke correctly.

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%, but description adds critical context beyond schema: the requirement that at least one of 'name' or 'type' must be provided, and the default scope for 'root' (current page). This adds value for an agent.

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 ('Search') and resource ('node tree'), and clarifies search criteria (case-insensitive name substring and/or exact node type). It distinguishes from siblings like 'scan_nodes_by_types' by combining both filters and returning a flat array.

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?

Clearly states requirements ('At least one of name or type is required') and optional scoping ('Scope to a subtree with root'). Implicitly guides when to use (searching by name/type) but does not explicitly mention when not to use or alternative tools.

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