search_templates

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the tool is safe and idempotent. The description adds behavioral clarity by detailing the five distinct search modes and their parameters (e.g., 'patterns' mode uses 2700+ templates for summaries), without contradicting annotations. The explanation of 'patterns' as lightweight summaries is extra context beyond annotations, but it lacks details on pagination behavior or result format, keeping it from a 5.

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 a single, well-structured sentence that efficiently enumerates all five modes and their purposes without redundancy. Every clause adds value (e.g., 'lightweight workflow pattern summaries mined from 2700+ templates'), and it's front-loaded with the main action ('Search templates with multiple modes').

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 13 parameters, no output schema, and rich sibling context, the description is remarkably complete. It covers the core behavior (five search modes), when to use each, and hints at return differences (e.g., 'patterns' yields summaries). With readOnlyHint and idempotentHint annotations, no additional safety info is needed. The only minor gap is no explicit mention of result pagination, but the schema's offset/limit parameters suffice.

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 description coverage is 100%, so the schema already documents all parameters. The description adds value by grouping parameters by search mode (e.g., 'query' for keyword, 'nodeTypes' for by_nodes), providing context not in the schema. However, for parameters like 'category' and 'targetAudience', the description only restates what the schema says, offering no deeper semantics, so it doesn't fully reach a 5.

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 searches templates with multiple modes, enumerates each mode with its specific use case (e.g., 'searchMode=keyword' for text search, 'by_nodes' to find templates using specific nodes), and distinguishes itself from siblings like search_nodes (which likely searches for nodes, not templates). The explicit listing of five search modes provides a precise scope.

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 tells when to use each mode (e.g., 'Use searchMode=keyword for text search, by_nodes to find templates using specific nodes'), which directly guides the AI agent in selecting the right approach. It implies that for template-related searches this tool is appropriate, while siblings like search_nodes are for node-level searches, providing clear separation of concerns.

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