screen_companies

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds genuine behavioral detail beyond them: entities whose currency lacks a current ECB rate are silently excluded from revenue filters, and revenue_year selects on latest reported revenue year rather than fiscal year N for all entities. Return shape is left to the output schema.

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?

Purpose and the list-vs-single routing are front-loaded, followed by terse backtick-labeled parameter notes. No filler sentences; the length is proportionate to a 13-parameter tool.

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?

The output schema covers return values, and the description handles several tricky filters. But for a 13-parameter, zero-coverage schema it omits the sector/gics_sector distinction, limit/pagination behavior, and bankruptcy_flag semantics, leaving real gaps an agent must guess at.

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%, so the description carries the full burden, and it compensates well for the parameters it touches (min/max_revenue currency + spot-rate caveat, country as ISO-2, revenue_year semantics, min_quality_grade and sort_by enumerations). However roughly eight of thirteen parameters (limit, sector, gics_sector, auditor_name, min/max_employees, bankruptcy_flag) get no explanation, and the overlapping 'sector' vs 'gics_sector' pair is left ambiguous.

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 and resource ('Filter the Hub-Equity universe') with the criteria domain named. It explicitly distinguishes itself from single-entity siblings with 'Use this when the user wants a LIST of companies matching criteria, not a single company.'

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 clear when-to-use context plus two concrete example queries and a when-not ('not a single company'). It does not name the specific alternative tool to use for single-entity lookups (e.g. find_entity / get_entity_profile), so routing requires inference.

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