journal_health

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

With no annotations, the description carries the full burden. It does add one genuinely useful behavioral fact — hand-written captures only, AIEX entries excluded so metrics aren't inflated — which an agent could not infer elsewhere. However, it says nothing about whether the call is read-only, whether it's expensive to compute, or whether results are cached/stale, so the safety and cost profile remains undisclosed.

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-loaded one-line purpose followed by a scannable bullet list of tracked metrics and a closing statement of what is returned. Every line carries information; the only mild cost is that the metric list is longer than strictly needed for tool selection.

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?

An output schema exists, so the description need not detail return values, and it wisely restricts itself to a one-line summary of the return. For a zero-parameter read tool, the description plus output schema gives an agent enough to call it correctly; only the lack of any comparison to similar stats tools leaves a small gap.

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 of 4 applies; there is nothing for the description to clarify or compensate for on this dimension.

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 concrete deliverable — a KPI dashboard plus coaching recommendations over journal practice — and enumerates exactly which metrics it computes (capture velocity, insight velocity, days since Review, unanswered questions, synthesis activity, template balance). That enumeration distinguishes it from generic siblings like get_stats, though it never names those siblings 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?

The content implies when the tool is useful (periodic practice check-ins, coaching), but there is no explicit when-to-use statement, no exclusions, and no routing against near-neighbors such as get_stats, knowledge_progress, or get_breakthroughs. Usage is left to inference from the KPI list.

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