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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description still adds useful behavior — NAICS version defaulting to 2022 (or 2017), defaults like 'newest year' for area rankings, and the distinction that zip rankings are by businesses while others are by employees. No auth, rate-limit or pagination behavior beyond limit/offset is disclosed.

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?

Dense but largely justified for a genuinely multi-mode tool; the primary purpose is front-loaded. The problem is structure: a single semicolon-chained paragraph mixing four distinct modes makes it hard to parse, and mode headings or line breaks would have cost nothing. Length is defensible, formatting is not.

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 an output schema present, return values need not be described, and with 8 zero-required params the description must carry the routing burden — which it largely does, covering every mode and its trigger parameters. Minor gaps: no overview of how the modes conflict if several optional params are supplied together, and no pointer to list_filters for the full filter surface in the description text.

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 100%, so the baseline is 3, but the description goes well beyond it: it enumerates the undocumented `filters` keys per mode (version, code, level, parent, sector, limit, offset; year, state, sort; metric, frequency, from, to, seasonally_adjusted), gives worked examples (filters={"level": 2}, parent '00', change_1y_pct|value) and concrete code formats ('522110', '31-33'). This is exactly what the opaque `filters` object needs.

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?

Opens with a specific verb+resource ('Industry and sector classification of a company') and names the classification schemes (revenue-based sector/industry, NAICS, SIC), which no sibling covers. However, the first line undersells the real scope — the tool is also a NAICS code tree browser, an area-statistics lookup and an economic-metrics API — so an agent skimming only the opening sentence would misjudge it. Sibling differentiation is implicit 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?

Gives real conditional routing: no company → official NAICS code list; with industry_code + area_stats → area employment figures; with metrics → statistical series, with sub-modes values/series/ranking each explained. It does not, however, name alternative tools (e.g. get_sector_industry_performance) for overlapping needs, and the 'use search_symbols if you only know the name' hint lives only in the schema, not here.

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