graphiti_search

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds that the tool is advisory-only, never broker truth, and fails closed with graphiti_unavailable, providing useful behavioral context beyond 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?

The description is moderately long but every sentence adds value: purpose, return format, usage guidance, authority warning, and failure mode. It is front-loaded with the core purpose. A slight reduction would still be effective.

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 sufficiently explains return values (advisory facts with validity windows) and data sources. It also covers failure mode and authority level, making it complete for decision-making.

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 both parameters. The description does not add parameter-specific details beyond what the schema provides, supporting a baseline score of 3.

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 is a hybrid search over a temporal knowledge graph, returns advisory facts with validity windows, and gives an example query. It distinguishes itself from siblings by stating it complements rag_search/onyx (semantic) and query_codegraph (structural).

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 says when to use: for temporal queries like 'what was true / what changed / what preceded what'. It also mentions failure mode (fails closed) and contrasts with other tools, but does not explicitly state when not to use.

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