recall_with_graph

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description nonetheless discloses the execution model (hybrid recall seeding, BFS over memory_edges bounded by hops) and the result shape (composite score ranking with hop_distance and provenance). It omits any note that deeper traversal is more expensive or how task_id caching affects results.

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?

Four tight sentences, front-loaded with the mechanism and followed by return shape and usage trigger. No filler or restated title.

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?

No output schema exists, and the description covers return values, traversal behavior, and the selection context, while annotations carry the safety profile. Enough for an agent to invoke it 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 description coverage is 100%, so every parameter is already documented; baseline is 3. The description echoes `hops` as traversal depth and frames `q` as the seed for hybrid recall, but does not clarify `weight_threshold`, `task_id` cache semantics, or how `project_id` narrows traversal, so it adds little beyond the schema.

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?

States a specific verb + resource (search memory) plus a differentiating mechanism: Knowledge Graph expansion seeded from hybrid recall with BFS over memory_edges. An agent can distinguish it from the sibling `recall` purely from this text.

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?

"Use when you want broader context — related decisions, connected incidents, derived learnings" gives a clear positive context for selection. It does not explicitly name the plain `recall` sibling or state when the cheaper non-graph path is preferred, so routing is implied rather than complete.

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