get_active_problems

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile needs no restatement. The description adds ordering and returned fields, but omits the important behavioral defaults: limit 25, min_severity defaulting to 'average', and unacknowledged_only defaulting to true, meaning acknowledged problems are silently excluded from a result described as 'current unresolved problems'.

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?

One front-loaded sentence with no wasted words; scope comes first and ordering second. It is terse to the point of under-specification rather than verbose, so the efficiency is real but bought at the cost of missing defaults.

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?

A six-parameter, zero-required tool with no output schema and several default-true/default-value filters needs the description to explain what the returned set actually contains. As written, an agent cannot know that suppressed and acknowledged problems are excluded by default, so it risks misreporting the problem set as 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?

With only 50% schema description coverage, three parameters (limit, include_suppressed, unacknowledged_only) carry no explanation anywhere, and the description does not compensate. It also gives no hint about the severity scale semantics or wildcard filtering supported by host/group, leaving the default-driven filtering behavior 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 resource and scope: 'Current unresolved problems', plus the ordering ('newest first') and the fields returned (host, severity, age). An agent can tell it apart from get_triggers and get_problem_events at a high level, though no sibling is named explicitly.

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?

There is no when-to-use or when-not-to-use guidance, and no routing to alternatives such as get_problem_events (which presumably covers problem history) or get_triggers. In a sibling set this dense, the agent must infer that this is the 'currently active only' view on its own.

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