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

The description presents a pure read/enumeration operation over a company register, but the annotations declare readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=true. An agent reading the description would treat this as a safe listing call, while the structured metadata warns of a destructive, non-idempotent write-like operation. The description does nothing to reconcile this, so it contradicts rather than supplements the 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, front-loaded with the resource and its fields, then the concrete next-step purpose. No filler. The field enumeration is dense but each item (risk class, override, decision count) informs how the agent will interpret the result.

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 no input schema and no output schema, the description carries the return-shape burden and does so by listing the fields each register entry exposes. It also tells the agent the downstream purpose (obtaining system_id), which is the only contextual dependency for this tool.

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?

There are zero parameters, so the baseline is 4 and there is no parameter semantics to add. The description does spend its words on what each record contains, which is useful because no output schema exists, but that is return-content detail rather than added parameter meaning.

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 the specific resource (this company's register of AI systems) and enumerates the fields each record carries: purpose, role under the EU AI Act, risk class, human override, and decision counts. The closing line 'Use it to find the system_id to log against' separates it from register_ai_system and points at the logging flow, so an agent can distinguish it from siblings without opening a schema.

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?

It gives a clear use case: retrieve systems so you can obtain a system_id to log decisions against. It does not explicitly state exclusions (e.g. 'do not use this to create or modify systems, use register_ai_system'), so the routing is implied rather than spelled out, which keeps it below a 5.

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