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

Adds substantial context beyond the annotations: the permission gate family/permissions.py::can_view_resource, OWNER-scoped visibility limited to the sharer's own transactions, and a deliberate no-existence-oracle error behavior. Annotations already cover read-only/idempotent safety, but these operational details are genuinely valuable.

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 purpose, then gives permission behavior, Args, and Returns in compact sections. No sentence is filler — the scope note and no-oracle detail each earn their place.

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?

No output schema exists, but the Returns section describes the response and the error case. Combined with annotations and complete parameter documentation, an agent has enough to call the tool 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?

Schema coverage is 0%, so the description carries the full burden and documents all four parameters: account_id purpose, limit default and max 200, and start/end date format. It leaves date inclusivity and timezone unspecified, so not exhaustive.

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: 'Transaction history for an account another family member shared with you.' It further distinguishes itself from own-account sibling tools by noting it reads another user's rows and is OWNER-scoped, so an agent can tell it apart without opening schemas.

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?

Pins usage to accounts shared by a family member and discloses the permission gate, making clear this is not for the caller's own accounts. It does not explicitly name get_account_history or list_shared_accounts as alternatives, so exclusion routing is left implicit.

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