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

Goes well beyond the annotations, which already declare readOnly/idempotent/non-destructive. It discloses the 90-day lookback cap, a quota model ('Firma ze zmianami = 1 z puli (24 h); firmy bez zmian nie zużywają puli'), and a privacy rule ('Osoby wyłącznie z person_id, nigdy PESEL') — exactly the billing and data-handling facts an agent cannot get from 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 the core action and date bound, and every clause carries distinct information (categories, modes, return shape, privacy, quota). It is a dense semicolon-chained block, though, and the quota/return/privacy details are crammed into the same run-on rather than separated.

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?

No output schema exists, and the description compensates by listing the returned fields (krs, name, type, before, after, detected_at, details). Combined with the enumeration of change types, the two scoping modes, the date limit, and the quota rule, an agent has everything needed to call and interpret it.

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 three parameters and their formats. The description still adds value: it ties 'types' to the actual category names (ocena, krz, sprawozdanie, dane_finansowe, zarzad, vat) and attaches the 90-day limit to 'since', which the schema does not say.

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 resource and action: a change feed ('Zmiany od daty since') over watched companies, enumerating the six change categories it reports (ocena A–E, KRZ, sprawozdanie, rocznik, zarząd, VAT). It also spells out the two scoping modes (no krs = watchlist, with krs = single company). It is clear but never names a sibling such as firma or sprawozdanie, so the agent must infer the routing itself.

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?

Concrete usage context is given: supply krs for one company, omit it to poll the watchlist, and the watchlist is managed elsewhere via REST /api/v1/watchlist. The hard 90-day window is stated as a usage constraint. What's missing is an explicit 'use X instead when you need Y' pointer to sibling tools or a when-not-to-use case.

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