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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds behavioral details like 'newest first' and the notion of a 'feed', which imply pagination or a stream, and it clarifies the scope (canton/period). No contradiction with annotations.

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 sentences with no filler. The first sentence states the resource, order, and content; the second provides a concise use-case. It is front-loaded and efficient.

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?

While the tool has no output schema, the description does not specify the fields returned per publication or pagination behavior. It says 'feed' implying a list, but an agent would not know what details each entry contains. This is a gap given no output schema to compensate. The limit default is in the schema, so that is covered, but the return structure is not.

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 descriptions for all four parameters. The description reinforces the meaning by grouping the kind values (new registrations, changes, strike-offs, bankruptcies) and tying the canton/since parameters to the 'what moved' use case, adding semantic value beyond the schema's individual field descriptions.

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 clearly states the tool lists registry publications (SHAB/FOSC) with a specific ordering (newest first) and enumerates the event types covered (new registrations, changes, strike-offs, bankruptcies). This distinguishes it from sibling tools like list_new_companies (which likely only covers new registrations) and search_companies (which is a general search).

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 phrase 'The feed to answer what moved in a canton or a period' gives clear context on when to use it: for tracking changes over time or location. However, it does not explicitly mention alternatives or exclusions (e.g., 'use list_new_companies for only new registrations'), so it stops short of a full routing guide.

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