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

Annotations already cover read-only, idempotent, non-destructive and open-world. The description adds genuinely new behavior: results carry source page citations, max shares come with a stated reason, and the note that the hub forwards the question to the Moja Pasza server explains the open-world backend. It stops short of output format or pagination detail, but the annotations carry the safety profile.

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 the core value (which nutrients for which species/age), then progressively narrower extras (max shares, laying-hen dose, no-parameter behavior). Dense but every clause carries information; the bracketed module/URL attribution is the only 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?

For a two-optional-parameter read tool with no output schema, the description explains return content in detail: nutrient sets per group, period-specific max raw-material shares with reasons and sources, and typical daily intake for hens in lay. Only the exact response shape is unspecified, which is minor.

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% with an enum and examples, so baseline is 3. The description adds that the period lookup is fuzzy ('okres albo jego fragment' is reflected in examples like 'powyżej 45', 'starter') and that both parameters are optional since a bare call lists species and periods — useful meaning 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 names a specific resource (nutritional norms for 6 poultry groups and their age periods) and enumerates exactly which nutrients and extras are returned (energy, protein, Ca, P, fiber, sodium; K, Mg, microelements for breeding flocks; max raw-material shares; daily feed dose for laying hens). This is clearly a reference lookup, not a calculator like pasze_policz_mieszanke or an ingredient catalog like pasze_skladniki_paszy.

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 by the data described, and it does state the no-parameter behavior ('Bez parametrów zwraca listę gatunków i okresów'), which is a real invocation hint. However, it never says when to prefer this over the sibling calculation or ingredient tools, and gives no exclusions.

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