netintel_extract_table

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

No annotations are provided, so the description carries the full burden, but it does disclose useful behavioral traits: the backing model (Claude Haiku, implying cost/latency profile) and the exact return shape (columns + rows). It says nothing about size limits, behavior on non-tabular input, failure modes, or cost, and it is cut off mid-sentence, leaving the behavioral picture incomplete.

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 purpose is front-loaded well, but the description terminates mid-clause with "into…", leaving a visibly unfinished sentence and unresolved content. It is also a single run-on sentence that tries to carry purpose, mechanism, and output in one breath.

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 one-parameter tool with no annotations and no output schema, the description covers the essentials — accepted input forms and the returned structure (columns + rows). The truncation and the absence of any input constraint (size, HTML vs. plain text handling) leave gaps for an agent deciding whether to call it.

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?

There is a single parameter with 0% schema description coverage, so the description must supply the semantics. It partially does: the input is messy text or HTML content ("pasted tables, HTML tables, and delimited text"), implying content rather than a URL. It never states format, size, or whether a URL is accepted, so the one undocumented param is only partly compensated for.

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 and resource ("Extract tabular data") and adds the mechanism ("detects columns and rows") plus the output shape ("clean structured JSON (columns + rows)"), so the purpose is unambiguous. It does not, however, distinguish itself from near-neighbors in the large extract family (netintel_extract, netintel_text_to_json, netintel_schema_parse), so the agent must infer the boundary.

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?

Input types named — "pasted tables, HTML tables, and delimited text" — imply when the tool applies, which is real but indirect guidance. There is no explicit when-not condition and no sibling alternative is named, so the agent gets no routing help among the many other extraction tools.

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