find_sic

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

Annotations already declare a read-only, closed-world lookup, and the description still adds real behavioral detail: bundles are approximate code sets with stated inclusions and misses, word matching is whole-word only, results are capped at 15 and sorted by code rather than relevance. The one gap is that the 'pass a bundle's id in sic_codes' step cannot actually be executed against this one-parameter schema, leaving the agents' next call unclear.

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 opening sentence is properly front-loaded and the workflow ordering is preserved, but the rest is a dense run-on that mixes lookup instructions, output-reading instructions, and answer-formatting advice with no separation. The final 'Name the codes you used in your answer' is useful but reads as output policy rather than tool documentation.

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?

An output schema exists, so return values need not be explained, yet the description insists on describing bundles, ordering, and caps while omitting the one thing that matters more: how to actually invoke the bundle path given there is no sic_codes parameter. The mismatch between the described two-stage workflow and the single 'text' input leaves an agent likely to attempt an invalid call.

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% for the single 'text' parameter, so the description has to carry it, and it partly does by giving examples of acceptable input ('AI, coffee shop, barber, e-commerce'). But it never states the length constraints and spends its parameter-related wording on 'sic_codes', which is not a parameter of this tool, creating a semantics mismatch with 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 first sentence gives a specific verb and resource: 'Find SIC 2007 codes for an industry', which an agent can act on immediately. It does not differentiate itself from related siblings such as breakdown_by_industry or largest_industries, so the agent must infer the boundary itself.

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 does give workflow guidance: query everyday words first, treat returned bundles as approximate, drill into codes, then 3-digit groups, and pass a group code for broad industries like 'cleaning'. However, no guidance is given on when this tool should be preferred over the many industry-counting siblings, and the workflow references a 'sic_codes' parameter that does not exist in this schema.

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