netintel_event_classify

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

With no annotations present, the description carries the full burden and does add real value beyond structured fields: it discloses the cost profile ('cheap', 'free-ish' screening), the underlying model ('one tiny Haiku call'), latency ('fast'), and the exact return contract (is_event, confidence, one-line reason). It stops short of describing failure/ambiguity handling or any rate limit, but this is well above what the schema offers.

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 value proposition and cost rationale are front-loaded, which is good structure, but the single run-on sentence ends in an ellipsis with the thought unfinished — a defect rather than an economy. Content that remains is dense and earns its place.

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?

There is no output schema, so the description correctly enumerates the returned fields (is_event, confidence, reason), which is a genuine asset. However, it leaves two of three inputs unexplained and is truncated, so an agent cannot fully reconstruct the calling contract from the description plus schema.

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% across three parameters, so the description must compensate and does not. It never mentions 'timezone' or 'posted_at', both of which are load-bearing for deciding whether text describes a dateable future event, and the truncated sentence leaves the input contract undefined.

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 names a specific verb+resource — a binary 'is this a dateable event?' classifier over social and web text — and implicitly positions itself against full extraction ('only pay for full extraction on the ones…'), which maps onto the sibling netintel_event_extract. It is clear, though the distinguishing sentence is cut off mid-thought.

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 workflow is implied rather than stated: screen every post here, then escalate to full event extraction only for positives. No explicit when-not-to-use or named alternative is given, and the truncated clause that would have named the extraction step removes the strongest routing signal.

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