pm_observe

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

With no annotations, the description carries the burden itself and does disclose the key trait: this persists to durable storage ('落盘') and is manual-only versus auto-observation. However it says nothing about permissions, reversibility, deduplication, or what happens on repeated calls, leaving real behavioral gaps.

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 tight sentences, front-loaded with the core action followed by the usage condition. Zero waste.

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 simple 2-parameter, no-output-schema tool, the description covers the essential why and when. It is nearly complete; only the durability/return behavior on the persistence side is unaddressed, which is minor given the rich schema.

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% and the enum's 'auto-classify if omitted' behavior is described in the schema, so the burden is already met. The description adds no parameter-level meaning beyond noting that text should preserve the original wording, which is minimal value over 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?

Clear verb+resource: 'explicitly record one thing.' It distinguishes the manual path from automatic daily observation, letting an agent grasp the intent. It does not differentiate from siblings like pm_diary or pm_pin that also persist content, so it stops short of a 5.

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?

Explicitly states the when-not (daily conversation is auto-observed) and the when (only when you judge a sentence important enough to persist). This is real routing guidance, though it names no specific sibling alternative for comparison.

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