deep_analyze

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

With no annotations, the description carries the full burden and does so well: it discloses that heavy reasoning runs off-context so only the conclusion enters the agent's context, that backend selection is DeepSeek when configured else local Ollama, and that failure degrades to raw structured data with analysis=null. That is exactly the behavioral context an agent needs before committing to an expensive call.

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?

Purpose is front-loaded in the first line and the Args block is compact and scannable with no duplicated schema noise. A couple of backtick/formatting artifacts and slight restatement of the off-context point keep it just short of ideal tightness.

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?

For a six-parameter tool with an output schema already documenting returns, the description supplies everything else missing: data-gathering behavior, backend choice, latency/cost implication of heavy reasoning, tier tradeoffs, and the degraded fallback. Nothing needed to call it correctly is absent.

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 0%, so the description must compensate and it does: all six parameters are explained, including the interaction where lat/lon/radius_nm load a focused area bundle, that model applies only on the Ollama fallback, and that tier maps to deepseek-reasoner vs deepseek-chat. The tier semantics in particular are entirely absent from 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 opening line names a specific verb and resource — a reasoning model reasoning deeply over live intel — and the body clarifies the mechanism (gathers situation/area bundle/jamming/anomalies, feeds an off-context LLM). An agent can tell this apart from data-returning siblings, but the description never names an alternative such as get_situation or intel_brief, so routing differentiation is implied rather than stated.

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?

It gives clear contextual guidance: lat/lon triggers the focused area bundle 'loaded PRIMARY', and tier=reason is for judgement while tier=fast is quicker/shallower, which is genuine selection advice. It also documents the no-backend fallback path. What's missing is an explicit when-not rule against the other analysis/summary siblings.

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