policy_ingest

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

With no annotations provided, the description carries the full burden and mostly succeeds: it discloses the propose-only default, the exact condition that causes writes (confirm=true), and the return format (draft + diff with per-field provenance). Gaps remain around permissions, validation failures, and idempotency, but the core mutation safety profile is explicit.

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 core purpose, then immediately addresses the critical default and return shape. Every sentence contributes useful scope or safety information, and there is no filler.

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 two-parameter ingestion tool with no output schema and no annotations, the description covers purpose, input scope, mutation behavior, and return semantics. It could be more complete about error behavior or supported document variants, but the essentials an agent needs to call it correctly are present.

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 must explain the two parameters. It does: 'path' is scoped to a LOCAL file path, and 'confirm' is framed as the gate that overrides the propose-only default. That meaningfully compensates for the empty schema, though it does not specify accepted file extensions or path syntax.

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 ('Ingest') and concrete resource ('declarations-page-style document (JSON or simple text) from a LOCAL file path'), and adds return shape ('draft + diff with per-field provenance'). It distinguishes itself from read-oriented siblings (policy_list, policy_get) by being the only ingestion tool, though it does not name them 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?

Gives clear context for when to use it: local files in declarations-page or household_profile JSON form. It also flags the crucial default behavior around confirm=true, which is the main decision an agent must make before invoking. It does not mention alternatives explicitly, but the usage context is clear.

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