pending_updates

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

With no annotations, the description carries the full burden and does so: it declares read-only behavior, explains the underlying mechanism (apt-get simulation, dnf updateinfo/check-update), and explicitly states 'never installs' so the agent knows no mutation occurs. It also names the exact error condition (pkg_manager_not_supported).

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?

Front-loads the purpose, then compresses platform mechanics, return shape, and error into a tight set of clauses. Every sentence adds information with no filler.

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?

Despite having no output schema and no annotations, the description documents the return JSON structure, the read-only guarantee, platform coverage, and the failure mode. An agent has everything needed to call and interpret it 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 description coverage is 100% and the single instance_id parameter is fully documented in the schema, including the '<account>/<name>' and 'custom/<name>' formats. The description adds no parameter detail beyond that, so the baseline 3 applies.

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 resource and scope: 'Pending package updates on one instance' with the exact data returned (security vs total counts, reboot-required, sample packages). No sibling tool covers package updates, so it is unambiguously distinguishable from the fleet/log/aws-family tools listed.

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 scope ('on one instance') and the platform note imply when it applies (checking patch state before maintenance), but there is no explicit when-to-use vs. an alternative tool, nor any stated prerequisite beyond the instance id. Usage is implied rather than directed.

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