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

Annotations already cover readOnly/idempotent/destructive hints, and the description adds substantial behavior beyond them: the 20-row cap with no offset paging, top-of-ordering semantics, the default exclusion of suspended companies matching website behavior, the `suspended_hidden` response field, and the `suspended=include` override. No contradiction with annotations.

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?

Three tight sentences plus a compact filter list, with the core purpose first, then limits, then positioning, then the suspended nuance. Every sentence earns its place; the suspended explanation is the longest part but carries unique behavioral information that justifies its length.

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 an 8-parameter tool with no output schema, the description covers limits, default behavior, overrides, and one response field (suspended_hidden). The only minor gap is the absence of any indication of which columns/fields the returned rows contain — though 'screen' implies company rows, the full return shape is unspecified.

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. The description adds genuine value for the suspended parameter by explaining the default-exclusion behavior and the response counter, which the schema only partially conveys. The filter list groups the parameters coherently, though it mostly mirrors schema names for the other seven parameters.

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 ('Screen') and resource ('the ASX universe') with named dimensions (dilution risk, cash cover, market cap, industry). The phrase 'A discovery tool, not an extract' plus the sibling names (get_cash_runway, get_dilution_snapshot, etc.) make it unmistakably distinct: this is a universe-wide screener while the siblings are per-company data lookups.

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 positions the tool as a discovery tool for screening the universe, which implies it is for breadth-first exploration rather than targeted retrieval. It also states what it is not ('not an extract') and its hard limit (at most 20 rows, no paging). It does not name a specific sibling alternative, but the get_* sibling set makes the boundary clear enough.

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