sysknife_collect_diagnostics

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is fully covered and the description's 'Read-only' adds nothing. The one genuine contribution is the 500-line cap on the journal output, which is useful behavioral context. Missing are privilege requirements (journal access often needs group membership or root) and whether output is truncated or paginated.

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?

It is short, but the first sentence is largely a tautological restatement of the name and title, and the second is a sentence fragment lacking a verb. The valuable content (journal log, last 500 lines) is present but buried behind name-echo padding.

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 no output schema, the description must convey what comes back; 'last 500 lines' does that partially. However, for a zero-param read tool sitting among ~50 siblings including sysknife_get_journal_log, sysknife_get_service_logs and sysknife_doctor, the description never establishes its niche, which is the main thing an agent needs to call 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?

The tool takes zero parameters, so the baseline is 4. The description does not need to explain any input, and nothing it says contradicts the empty schema.

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 second sentence does name the concrete resource — the recent system journal log, capped at the last 500 lines — but the leading sentence merely restates the tool name ('Read-only SysKnife action `CollectDiagnostics`'), and the stated purpose (generic diagnostics collection) is broader than the actual behavior (journal read). A sibling named sysknife_get_journal_log exists and is never distinguished, so an agent cannot tell whether this is the same data or a different slice.

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?

'for error diagnosis and troubleshooting' implies a usage context, which is more than nothing. But there is no explicit when-to-use vs when-not, and critically no mention of sysknife_get_journal_log or sysknife_doctor as alternatives — the agent must guess which journal-reading tool to pick.

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