graph_search

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

Describes the two-step process (vector_search then subgraph expansion) and output structure. While no annotations exist, the description covers key behavioral aspects, though it could explicitly state non-destructive nature.

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 concise paragraphs, front-loaded with the core definition. Every sentence adds value without redundancy.

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 the hybrid complexity and lack of output schema, the description sufficiently explains output ('both vector results and their graph contexts') and performance benefits relative to alternatives.

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?

Adds meaning to both parameters: 'query' is the vector search query (not documented in schema) and 'workspace_id' controls cross-project scope. With 50% schema coverage, the description compensates well.

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 explicitly states 'Hybrid search: vector search + expanded subgraphs', defining a specific verb+resource+mechanism. It distinguishes from siblings like vector_search and graph_get_node by explaining the combined operation.

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: 'Use when you need deep context around search results — faster than calling vector_search then graph_get_node for each result manually.' Also explains cross-project behavior with workspace_id.

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