Search Workspace Content

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

Beyond annotations (readOnly, idempotent), description discloses caching behavior: first call fetches all workspace nodes (may be slow), subsequent calls use in-memory cache with 30 min TTL. This adds significant behavioral context not covered by 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?

Well-structured: first sentence states purpose, followed by parameter list in docstring style, then returns and two paragraphs on efficiency and caching. Front-loaded and no wasted sentences, though could be slightly more concise.

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?

Covers main aspects: purpose, all parameters with defaults, return format, caching behavior, and performance implications. Omitted details like error handling or pagination are acceptable given the output schema and simplicity of the tool.

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 descriptions for each parameter. The description adds default values (limit default 50, fields defaults to all), return format, and groups parameters logically. This goes beyond the schema's individual parameter descriptions.

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 it searches across node names, SQL, column names, descriptions, and config values using the lineage cache. It distinguishes from siblings by specifying the data source and efficiency, but does not explicitly name alternative search 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?

Provides clear guidance on when to use: it is efficient for large workspaces and uses cached data after initial fetch. Also states requirement of populated cache and default TTL. However, does not explicitly mention when not to use or compare to siblings.

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