netintel_entity_extract

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

No annotations are provided, so the description carries the full burden. It does disclose the underlying model (Claude Haiku) and the return shape ('structured typed arrays'), which is useful, but says nothing about input size limits, latency/cost, failure modes, or whether extraction is deterministic.

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?

One front-loaded sentence that leads with the verb and resource, then details the entity types. The closing clause 'so agents can pull structured signals out of unstructured text' restates the obvious, and the trailing ellipsis suggests truncation rather than deliberate concision.

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?

With no annotations, no output schema, and 0% schema coverage, the description is the only documentation. It covers purpose, model, and rough return shape, but leaves input limits, the semantics of the 'types' filter when omitted, and output record fields unspecified.

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 coverage is 0%, so the description must compensate. It effectively documents the valid values for the 'types' filter by listing the entity categories, which the schema leaves as an unconstrained string array with no enum. It adds nothing about the required 'text' parameter's constraints (length, encoding).

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 (Extract) and resource (named entities from text) and enumerates the supported entity classes (people, organizations, locations, dates, emails, URLs, money, products). That enumeration distinguishes it from sibling extractors such as netintel_extract_contact, netintel_extract_invoice, and netintel_event_extract, which are domain-specific.

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 phrase 'pull structured signals out of unstructured text' implies the general use case, but there is no explicit when-to-use, when-not-to-use, or routing to the many sibling extractors that overlap (contact, invoice, event, table). With ~100 siblings, the absence of any alternative-routing guidance is a real gap.

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