snapshot_portfolio_nav

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

Goes well beyond the annotations: explains that re-running appends an immutable version and moves that date's representative, the exception when a scheduled capture with crypto evidence holds it, and that only derived valuations hit local SQLite with no broker state touched. This also explains why idempotentHint is false.

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 with the action and the gating condition, then behavior, then args. Dense but nearly every clause earns its place; the 'see deploy/ for a systemd timer' pointer is mildly incidental for an agent invoking the tool.

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 an output schema present, return values need no elaboration beyond the brief mention of a structured JSON envelope. The mutation semantics, scheduling interaction, and refusal rule are all covered.

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 full burden for the single parameter — naming its ISO YYYY-MM-DD format, today default, and the reason other dates are refused (collection uses current prices). That framing is unavailable anywhere in 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 verb and resource ('Store today's portfolio NAV snapshot for history and TWR') plus the storage target ('local write'). An agent can immediately distinguish it from read-side siblings like get_portfolio_returns and get_portfolio_summary.

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?

Explicitly names the trigger ('Only on an explicit request to store a snapshot now'), the automated alternative (scheduled 18:10 KST job), and the exclusion ('reading returns or history needs no snapshot'). No inference required.

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