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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: open access with no key, no data stored, benchmark substitution for omitted values, and the md-vs-json response mode. It does not describe latency or limits, but that is minor here.

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 structure is sensible: what it computes, how to feed it, what comes back, and reference links. The opening sentence is dense – a long enumeration of outputs – but each clause carries information an agent needs, and there is no filler. Slightly tighter front-loading would earn a 5.

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 a 27-parameter calculator with no output schema, the description covers what the result contains (financing gap, runway, monthly liquidity, cost drivers, scenarios), the output language and format, and the defaults behavior. Return-value detail is thin, but the enumerated output list compensates reasonably for the absent output schema.

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 96%, so nearly every one of the 27 parameters is already documented in the schema, and the description does not restate or clarify individual parameter semantics. It only adds the framing that all fields are optional and default to industry values, plus the role of own cost items and hires. That is the baseline 3 for a schema-heavy tool.

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 names a concrete verb (rechnet aus) and a concrete resource (erstes Gründungsbudget), then enumerates the actual outputs it produces (Startfinanzierung, Lücke im Betrieb, tiefster Kontostand, Liquidität Monat für Monat, drei Szenarien). This makes it clearly distinguishable from sibling finance tools like cap_table or gmbh_steuern, which cover different artifacts.

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 explains the operating conditions well – every input is optional, missing values fall back to industry benchmarks, no key is required, and nothing is persisted – and it says the response comes in German as text or JSON. However, it never states when to choose this over a sibling tool or when a founding-budget calculation is not appropriate, so the when-to-use guidance remains implied.

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