Task Statistics

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

Annotations already carry readOnlyHint, idempotentHint, and destructiveHint; the description adds value by stating 'Read-only' and, more importantly, disclosing the vault-scoping behavior — the tool operates on the session-active vault unless vaultPath is passed, and vaultPath always takes precedence. This precedence rule is real behavioral context not derivable from the annotations.

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?

Two dense paragraphs with no filler. The first sentence front-loads the full metric enumeration and defines overdue; the next sentence handles sibling routing; the second paragraph explains vault selection. Every sentence earns its place, with outputs first, alternatives second, and scoping semantics last.

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 and safety traits covered by annotations, the description covers the remaining essentials: exact return-metric groups, sibling routing, and vault-resolution preconditions. Minor gaps — the precise scope of the 'per-priority breakdown' and the reference date for the horizons — are small enough not to prevent correct invocation.

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 0%, so the description carries the burden. It compensates by explaining what vaultPath does (overrides the session-active vault) and its precedence. It stops short of describing the expected path format, but for a single optional string parameter, the core semantics are clear.

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 description opens with a specific verb and resource: 'Return aggregate task statistics for the whole vault' and enumerates the exact metric groups returned (total, incomplete, completed, overdue, upcoming-by-horizon, per-priority). It also defines 'overdue' inline ('due date passed and still incomplete') and differentiates from tasks.search, so an agent can distinguish it from its closest sibling without opening any schema.

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 explicitly routes to the alternative: 'Use tasks.search to get the individual task records', which tells the agent when this aggregate tool is not the right choice. It also provides operational context for vault resolution (session-active vault, vaultPath override with 'always wins' precedence). No when-not guidance is left to inference.

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