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

With no annotations the description carries the full burden, and it discharges much of it by detailing the response structure (1-5 frames, dominant shared principle, anchor piece, supporting kernels, frame-difference notes). It also explains the behavioral effect of agent_id (breaking self-recency bias). It does not disclose latency, cost, or write/read safety explicitly, but for a query tool the return-shape detail is substantial.

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?

Front-loaded with the PRIMARY signal and the key output distinction, then parameter guidance. Dense but every clause earns its place; no filler sentences.

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, so the description must describe return values itself, and it does so in detail (frames, anchors, kernels, difference notes). Combined with the depth semantics this is sufficient for correct invocation, though naming the nearest alternative would fully close the gap.

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 3 is the baseline. The description adds real meaning beyond the schema by explaining why agent_id matters (filters the agent's own recent deposits to break self-recency bias) and by reframing depth as answer granularity rather than just frame counts.

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?

Names a specific verb+resource ('ask the graph a question') and sharply defines the output form ('synthesized argument shapes — not a flat ranked list'). This distinguishes it from a generic search, but it never names the closest sibling (e.g. consult, search_corpus, question_reflect), so sibling disambiguation is left to inference.

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 'PRIMARY' label and 'Always pass agent_id' imply this is the default entry point, and depth values are tied to use cases ('quick single-frame answer'). However there is no explicit when-not-this-tool rule and no named alternative, so usage is only implied.

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