reflect

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

With no annotations, the description carries full behavioral disclosure. It reveals that it reuses the Graphify graph with no extra LLM cost, and importantly, it saves candidates as proposed insights (unless store_them=False), which is a side effect. It does not fully detail other behaviors like permission needs or response structure, but covers the key aspects.

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 succinct and well-structured: a brief opening sentence explaining purpose and side effects, followed by a clean Args list. Every sentence provides necessary information 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?

The description covers purpose, usage context, side effects, and all parameters. It mentions that candidates are saved as proposed insights, which gives workflow context. Since an output schema exists, the absence of return-value explanation is acceptable. Could mention prerequisites like graph state, but overall it is quite complete.

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?

The default schema coverage is 0%, so the description fully compensates by providing clear meanings for each parameter: project scopes to a project (with None special meaning), limit sets max candidates, and store_them controls persistence. This adds substantial value 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?

The description clearly states the tool's function with a specific verb ('surface') and resource ('cross-project analogies and non-obvious connections across memories'). It explicitly distinguishes itself from recall ('that recall cannot reach'), showing a clear differentiation from siblings.

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 implies when to use the tool (when cross-project analogies or non-obvious connections are needed) and contrasts it with recall. It also outlines the workflow with accept_insight/reject_insight, but it does not explicitly list alternative tools or state when not to use it.

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