ofw_check_freshness

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

The annotation declares readOnlyHint: true, implying no side effects. However, the description explicitly states that setting allowMarkRead: true 'marks it READ on OurFamilyWizard and stamps a co-parent-visible "First Viewed" time — irreversible.' This is a write operation that directly contradicts the readOnlyHint. The contradiction is serious and undermines trust in the tool's safety classification.

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?

The description is long but densely packed with necessary context: costs, use cases, state semantics, side effects, and alternatives. It's front-loaded with the core purpose and avoids fluff. It could be trimmed slightly, but every detail serves the agent's decision-making.

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?

Given there is no output schema, the description fully describes what is returned: live server counts per folder, and for each id: state, folder, sentAt, existsOnServer, and content comparison. It also explains the meaning of state and why existsOnServer is insufficient. Costs, side effects, and exclusions are covered. No missing information is evident for an agent to call this 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 100%, so each parameter has a baseline description. The tool description goes well beyond this: it explains the default behavior of folders when messageIds is absent, the max of 25 ids, why certain ids are probed freely, and the full implications of allowMarkRead including the irreversible mark-read side effect. It also clarifies that content comparison uses revision hash because timestamps don't change on edit. This is substantial added meaning beyond 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?

The description opens with a specific verb and resource: 'Cheaply confirm whether the local cache still matches OurFamilyWizard, WITHOUT running a full sync.' It clearly distinguishes the tool from a full sync and from ofw_status, which it names as the alternative for draft inventories. The purpose is unambiguous and immediately actionable.

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 gives explicit when-to-use guidance: 'Use this before asserting anything about current state — especially "draft X is still sitting unsent".' It also states when not to use it: 'For draftKeys, or a full live draft inventory, use ofw_status.' This is a clear routing decision with no ambiguity.

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