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

Annotations already declare readOnly, idempotent, non-destructive and open-world behavior, so the safety profile is covered. The description adds genuinely useful behavioral detail beyond that: missing feed dose and feed price fall back to built-in reference values, and that substitution is surfaced in an output field 'zalozenia', which lets the agent explain assumptions to the user. It also limits scope to feed costs only, so the agent will not misreport it as full profitability.

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 answer to the user's question is front-loaded in the first sentence, then the inputs and the optional margin are introduced in logical order. Sentences are short and purposeful, with the trailing module/URL attribution being the only arguably non-essential element.

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, two of them required, no output schema and an algorithmic rather than CRUD purpose, the description covers the computation logic, the optional inputs, the fallback behavior and the scope limit. The one remaining gap is that the output shape is only alluded to through the 'zalozenia' field, with no indication of what other fields the result contains.

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% and the schema already documents units, ranges and the fallback for pasza_g and cena_paszy_zl_kg, so baseline is 3. The description restates the same parameter meanings in narrative form and adds the notion that cena_jajka_zl enables a margin-after-feed calculation, but it introduces no syntax or format detail beyond 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 uses a specific verb and resource: it computes feed cost per egg and per flock per month, and it names the inputs (number of hens, daily egg collection, feed dose, purchase price) plus the optional margin over feed revenue. The closing sentence 'Liczy tylko paszę' sets a clear scope boundary that separates it from a general profitability calculator, though it does not name a sibling tool by name.

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?

Usage is implied rather than stated. The description assumes the caller supplies the farmer's own numbers and explains what happens when a dose or a feed price is missing (the defaults are drawn from the model and disclosed in 'zalozenia'). However, it does not say when to prefer this tool over sibling tools such as pasze_normy_drobiu or pasze_policz_mieszanke, and it does not state prerequisites or exclusions.

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