system_events

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

The readOnlyHint annotation already covers the safety profile, so the description's job is to add context beyond that. It does: it discloses the aggregation behavior (rolled up by type+action), the exact return envelope, and — most usefully — the truncation behavior plus the remedy ("narrow the window with a smaller since"). It stops short of stating whether the window is measured against event timestamps or receipt time.

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 one-line purpose before the structured Args and Returns blocks. Every element is load-bearing: no restatement of the name, no filler, and the truncation caveat is tied directly to the parameter that fixes it.

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?

There is no output schema, so documenting the return envelope ("events"/"returned"/"limit"/"truncated"/"total") is necessary and it is done. Combined with the readOnlyHint annotation, full parameter coverage, and explicit truncation handling, an agent has everything needed to call this correctly and interpret the result.

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 0%, so the description carries the full burden and mostly meets it: it gives the since range and default (1..86400, default 3600), enumerates valid event_type values (container/image/volume/network) that are absent from the schema, and explains that target comes from config. The target explanation is the weak spot — "Target name from config" doesn't tell an agent where to find valid values.

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 ("Recent daemon events") plus the scoping semantics ("over the last N seconds, rolled up by type+action"), which tells the agent exactly what granularity it will get back. No sibling tool covers daemon events, so this is unambiguously distinguishable and even self-labels as "[READ]".

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 gives per-parameter filtering guidance ("omit for all", "omit for the default"), which implies usage, but never states when to reach for this tool instead of overview, system_df, or system_info. No exclusions or alternatives are named, so the agent must infer the scenario.

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