Screen Companies

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

Annotations already indicate readOnlyHint=true, confirming safety. The description adds value by detailing what the tool returns ('matching companies with key metrics and pagination') and the scope of filters. No side effects or contradictions are present.

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?

Two sentences with no redundancy. The action, filtering dimensions, sorting, and return format are all front-loaded. Every word contributes meaning.

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?

Given the tool's complexity (18 parameters) and the existence of an output schema, the description sufficiently covers the query criteria, sorting, and paginated results. It does not explain the return fields (handled by output schema), which is appropriate.

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% with per-parameter descriptions. The tool description only lists the categories of filters (e.g., 'price range, volume') but does not add new meaning beyond what the input schema already provides. Baseline score of 3 is appropriate.

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 clearly states that the tool screens companies by financial metrics like price, volume, and cash runway. It uses specific verbs ('screen') and resources ('companies'), and it implicitly distinguishes from text-based search tools like 'search_companies' by focusing on quantitative filters. However, it does not explicitly differentiate from siblings like 'screen_must_raise'.

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 description does not provide guidance on when to use this tool versus alternatives. It does not mention exclusions, prerequisites, or complementary tools (e.g., 'use search_companies for text matching'). The agent must infer usage from the parameter list alone.

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