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

Annotations already declare a safe, idempotent, open-world read, and the description still adds substantial behavioral detail: zero-share ingredients are filtered out for the given age, a norm-coverage check for energy and protein is included, the no-soy substitution order (lupin, rapeseed meal 00, sunflower meal) is spelled out, and a fish-meal fallback with an explicit farmer-facing warning is described when protein cannot be closed. It also discloses that premixes, concentrates and legal prohibitions come along in the result.

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 core purpose and the usage condition are front-loaded in the first sentence, which is good. However, the remainder is a dense run-on chain of clauses that mixes output contents, substitution algorithm and tangential material about premix doses, concentrates and kitchen-leftover regulations, without paragraph or bullet structure, making it harder to scan than its length warrants.

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 five parameters, no output schema and a compound return value, the description carries the full burden of explaining results, and it largely does: ingredient list, filtering rule, norm check, substitution cascade and warning behavior. The gaps are the unexplained wojewodztwo/wyklucz interaction and the absence of any note on result size or shape beyond 'lista surowców'.

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, but the description earns extra credit by explaining what the variants actually change behaviorally — z_soja/soja_bez_gmo share a composition while bez_soi switches to a substitute cascade — which goes beyond the enum labels. It does not touch the wojewodztwo or wyklucz parameters at all, leaving those entirely to the schema.

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 specific verb and resource: it returns a starter list of raw materials for a poultry mix, given only species, period and variant. It distinguishes itself from the sibling pasze_dobierz_proporcje by stating that its output is already in that tool's input format, so the agent can see this is the upstream 'pick the ingredients' step rather than the 'compute proportions' step.

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 opening clause gives a clear activation condition: use it when the farmer supplies only species, period and variant. The downstream relationship to dobierz_proporcje is implied through the output-format statement. What is missing is an explicit negative case (when to skip this and go straight to proportions or to pasze_normy_drobiu), so it lands at clear context without exclusions.

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