truth_upsert_rule

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

With no annotations, the description carries the full behavioral burden, and it does disclose the important traits: this is a write that fans out to three separate stores (disk, RAM mirror, Firestore) and is gated on human confirmation. It omits failure semantics — what happens if one store succeeds and another fails, whether partial writes are rolled back, and what 'upsert' means for an existing section with the same title. Those gaps matter for a multi-target mutation.

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?

It is a single front-loaded sentence with no filler, and the operation and targets appear before the caveat. Minor awkwardness: 'both ... on disk, in RAM mirror, and in Firestore' pairs 'both' with three items, and the parenthetical caveat is tacked on rather than integrated.

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 6-parameter mutation spanning three persistence layers with a human-approval handshake, the description covers what it does, where it writes, and that confirmation is required — the core essentials. It lacks the retry/token flow detail and any statement about ordering or atomicity across the three stores, and there is no output schema to fall back on, so an agent still has gaps to fill.

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 100%, so every parameter (scope enum, file_path, section_title, content, user_confirmed, confirmation_token) is already documented in the schema, including the approval-token flow. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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 names a specific verb pair (create or update) and a specific resource (ground-truth rule or spec), plus the persistence targets (disk, RAM mirror, Firestore). That is enough for an agent to distinguish it from siblings like truth_search or truth_status without opening schemas. It stops short of explicitly stating how it differs from those siblings, which keeps it at 4.

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 parenthetical '(requires human confirmation)' signals a prerequisite and implies this is a gated write rather than a fire-and-forget call. However, it never states the actual sequence (that the call first returns PENDING_HUMAN_APPROVAL and must be retried with user_confirmed and confirmation_token) nor when to prefer a different tool. Usage is implied rather than spelled out.

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