novel_diagnose

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

With no annotations, the description carries the full burden. It usefully discloses the output-safety scope ('report contains only metadata ... never body text'), which is real added value, but never mentions side effects or that the tool can destructively clear the local event log via action=clear, nor any permission requirements.

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 tool's nature and operation, then the use cases, then the important metadata-only caveat. It is dense but each clause carries information; the length is justified by the multi-aspect diagnostic scope.

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?

For a tool with no output schema and no annotations, it adequately explains purpose, what is inspected, what the report contains (and excludes), and when to use it. The one gap is that the destructive clear action and report/events output differences are left entirely to the schema rather than flagged in prose.

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%, so all four parameters (book, days, root, action) are already documented including defaults and the 90-day cap; baseline 3 applies. The description adds a data-source framing (event logs, library root, data directory) but no parameter syntax or format detail beyond the 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?

States a specific action (reads local event logs, inspects the library root and data directory) and the concrete outputs (aggregation of tool calls/degradations/failures, high-frequency failure types, directory health, actionable suggestions). It is unmistakably a diagnostics tool versus the content-oriented siblings, though no sibling is named to make the contrast explicit.

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?

Gives explicit triggering scenarios — 'the panel can't list books', 'a feature seems not to work', 'error but can't see the reason' — which tells the agent when to reach for it. However, it names no alternative tools and gives no exclusions, so the routing is incomplete at the edges.

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