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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: that the tool returns signup URLs and that the student registers on that page themselves, which tells the agent not to look for an enrollment tool. It does not say how many items come back or whether results are ordered by date.

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?

Two short sentences with zero filler; the resource definition comes first and the external-signup caveat second. Nothing is redundant, though the phrasing is a field enumeration rather than a purpose statement, which slightly slows front-loading.

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?

There is no output schema, so the description carries the return-shape burden and does describe the four fields returned. For a one-parameter read-only list tool this is close to sufficient; the only real gaps are the count/ordering of results and confirmation of the optional subject filter.

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?

The single parameter 'subject' is never mentioned in the description, and schema description coverage is 0%. The enum values are largely self-explanatory subject names, so ambiguity is low and the baseline for a filter with a self-documenting enum is a 3, but the description does not confirm that subject filters the list or that omitting it returns all subjects.

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: free online trainings run by the platform's teachers, and enumerates the returned fields (topic, instructor, nearest date, signup page). It is clearly distinguishable from search_courses or get_course, though it never names the closest sibling get_free_consultation, so the agent must infer the free-training vs free-consultation split.

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 only implied: the reader infers this is a browse-list tool for free webinars. The sentence 'Uczeń zapisuje się sam na stronie (signupUrl)' usefully signals that enrollment is external and should not be attempted via a tool, but there is no explicit when-to-use versus get_free_consultation or search_courses, and no statement that the subject filter is optional.

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