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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds real behavioral context the annotations don't: it describes the response contents (start, gas added, final pressure, resulting mix, MOD) and prescribes a follow-up question about checking the mix at a planned depth. It stops short of describing the `assumed` fallback mechanics available elsewhere, but adds genuine value beyond the structured fields.

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 routing before examples, and every sentence carries signal. The two Croatian sample utterances ('dopuni mi bocu...') are somewhat bulky and partly redundant with the English example, though defensible given the tool's language parameter. Slightly long but well ordered.

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 19-parameter tool with nested bank objects and no output schema, the description covers the required inputs, the routing decision, and the shape of the answer, which is what an agent needs to answer the user. Advanced parameters (banks, method, heat_correction, use_booster) are left entirely to the schema, which is acceptable at 100% coverage but leaves no cross-cutting guidance on them.

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 schema already documents all 19 parameters, and the description mostly restates the same inputs (start pressure and mix, final pressure, supply gas). It does stress that start_pressure materially changes the result, but the schema description already says 'This changes the result a lot'. Baseline 3 is appropriate when the schema carries the load.

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 ('Top a tank up with a ready-made supply gas') and immediately enumerates the outputs (pressure added, resulting mix, MOD, gas density). It also distinguishes itself from siblings by scoping to ready-made supply gas versus pure O2/He, naming what_if and blend. An agent can route correctly without opening any schema.

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 routing rule: 'For a ready-made supply gas; to add pure oxygen or helium use what_if or blend.' It also gives concrete trigger utterances in two languages and a precondition ('Needs the start pressure and mix, the final pressure and the supply gas: ask if one is unknown, don't assume'). This is about as close to when/when-not/alternatives as a description gets.

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