itemprototype_get

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

The annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already cover the safety profile, so the description only needed to add contextual value — which it does by defining what item prototypes are and how they relate to discovery rules. No contradiction with annotations: 'Get' aligns with readOnlyHint=true and destructiveHint=false. However, no operational behaviors (auth, rate limits, or the has_more/total paging semantics mentioned in the offset param) are disclosed here.

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?

Exactly two sentences with the action verb front-loaded and zero fluff. The second sentence, a parenthetical-style definition of item prototypes, earns its place by disambiguating the domain concept, though one could argue it's conceptually nice-to-have rather than strictly necessary for calling the tool. The structure is appropriately sized relative to the tool's 11-parameter surface area.

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 read-only tool with 0 required parameters, 91% schema coverage, and an output schema handle, the description covers the essentials. The only remaining gap is that the description never explicitly tells an agent when to prefer it over item_get — the sibling it's most easily confused with — but the discovery-rule gloss largely bridges that gap. The output schema covers return-value semantics.

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?

With 91% schema description coverage, the schema's parameter docs carry the semantic load, and per the rubric the baseline is 3 even without parameter information in the description. The description adds no parameter-level detail, but that's acceptable here — the schema's param descriptions are thorough (e.g., the offset param documents paging behavior with has_more and total). The description correctly avoids duplicating this.

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 opens with a specific verb-resource pair ('Get item prototypes from Zabbix') that maps directly to the tool name, then adds a sentence explaining that item prototypes are template items created by discovery rules that dynamically generate actual items. This conceptual clarification implicitly differentiates it from siblings like item_get, item_create, and discoveryrule_get by situating the prototype in Zabbix's discovery flow.

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 usage context is only implied through the concept description — an agent must infer that this tool is for template-level items rather than live items. There are no explicit alternatives named, no when-not-to-use guidance, and no mention of when to prefer item_get or discoveryrule_get, despite 54 sibling tools being available. The distinct-from-item-get signal is present but implicit rather than stated.

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