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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is settled. The description nonetheless adds real non-structured behavior: L0–L3 resolution tiers with per-tier credit costs (10/20/30/50) itemised in credits_by_line_item, the _warnings entry flagging dimensional results, and that light_weight_mode is charged identically. Return format is also described since no output schema exists. This is close to a 4, but the tier/credit model is dense and partly redundant with the schema's light_weight_mode text.

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?

Front-loaded with purpose and primary identification logic before branching into alternatives. The block is long, but nearly every sentence (cost tiers, warnings, alternative tools, ordering caveat) carries operational information rather than padding.

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 no output schema, the description compensates by explaining the return shape (_resolution_level, credits_by_line_item, dimensional_breakdowns, _warnings, fact_ids positions) and typical pitfalls (multi-concept ordering is a recommendation only). An agent has what it needs to call and interpret results.

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 100%, so the schema already documents each parameter, establishing a baseline of 3. The description adds value beyond it: how line_items resolve through L0–L3 tiers and what _resolution_level reports back, and the ordering/cost consequences of the choice – semantics the flat schema does not convey.

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?

Specific verb+resource (fetch XBRL facts for a single filing by line-item name) with an example list. It explicitly carves out scope against siblings: 'Returns consolidated totals only' and routes slice/dimension work to get_dimensional_breakdown_by_fact_id / get_dimensional_breakdown_by_line_item, and fact_id lookups to get_filing_facts.

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?

Explicit when-and-how: identify the filing with filing_id OR ticker + fiscal_year (+ quarter); form_type defaults to 10-K with 20-F/40-F for foreign issuers; and fallback guidance when unsure of a name ('use list_filing_statements / get_filing_statement'). Alternatives are named by purpose, not just listed.

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