Installed Software

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond annotations, especially the error condition: 'A host with no agent inventory at all raises, rather than returning zero rows.' It also reveals OS auto-detection, which is not inferable from the schema.

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?

The description is compact and well-structured: a one-sentence resource definition, a usage paragraph, and an error-behavior paragraph. Every sentence earns its place, and the most important scoping information is front-loaded.

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 annotations covering safety/idempotence and an output schema covering return shape, the description supplies the remaining context: when to use it, how to constrain results, where to get the required hostname, and what happens for hosts without inventory. An agent has everything needed to select and invoke this tool correctly.

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 75%, and the description compensates for the only_updatable parameter, which has no schema description, by explaining it means 'just the outdated ones.' It also clarifies that name_filter searches by package name and reinforces that hostname is host-scoped with no estate-wide form. This adds real meaning beyond the schema without fully documenting every parameter edge case.

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 precise statement: 'Software installed on a host, from the openITCOCKPIT agent's inventory.' This clearly identifies the resource, the scope (single host), and the data source. It also distinguishes itself from the estate-wide update siblings by noting the host-scoped nature.

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 description explicitly tells the agent when to use alternatives: 'For updates across the whole estate use list_pending_updates or list_pending_security_updates.' It also gives concrete usage guidance by recommending name_filter and only_updatable, and it explains that hostname is required and can be obtained from specific sibling tools.

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