Installed Software

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the platform-dependent data sources (Windows uninstall registry vs Linux package database), which tells an agent why results may differ across hosts and why some software may be missed.

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 tight sentences with no filler; the core purpose and the platform data sources are front-loaded in that order.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers the key cross-platform behavioral caveat. The remaining gap is the limit parameter's default/capping behavior, which matters for an agent deciding whether results are complete.

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 is a single parameter (limit) with 0% schema description coverage, so the schema carries no meaning. The description's word 'bounded' implies the inventory is capped by that limit, but it does not state the default value, the 500 maximum, or pagination/truncation behavior, leaving most of the parameter's semantics undocumented.

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 verb and resource — returning an installed-software inventory — and adds that it includes versions and publisher metadata, which distinguishes it from the bare 'software_changes' sibling. It does not explicitly contrast with 'software_versions', so the boundary between those two inventory-style siblings is left to inference.

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 never says when to use this tool instead of software_versions or software_changes, nor any precondition (e.g., permissions, platform requirements beyond the OS data sources). Usage must be inferred entirely from the one-line scope statement.

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