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

Annotations already declare this as read-only, idempotent, open-world, and non-destructive. The description adds behavior beyond those annotations: results are newest first, each item is brief, state filtering is supported, and after-based pagination works from the last seen id. It does not cover auth or rate limits, but for a read-only list tool the added context is substantial.

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 front-loaded with the resource, ordering, and endpoint, then moves into parameter guidance and the get_act alternative. The final instruction about calling it an errand and formatting the id is useful context, but it slightly lengthens the description beyond core invocation guidance.

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 three-parameter, read-only list tool with no output schema, the description explains what each returned item contains in brief ('what each is, where it stands, and when its review ends'), how ordering works, and how filtering and continuation work. It leaves out explicit mention of limit and any statement about whether more pages exist, but the essentials for calling 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 coverage is 100%, so the baseline would be 3. The description adds meaning beyond the schema by explaining that state can be used to isolate one status and by giving SUBMITTED as a meaningful example ('work waiting on your review'), and it clarifies after as reading on from the last id you saw.

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 states a specific verb and resource: listing the Principal's ACTs, newest first, each in brief. It also distinguishes this from get_act by saying 'Read one whole with get_act,' so the agent can tell the list tool apart from the detail tool.

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?

It explicitly explains when to use the state filter ('Give state to see one state, such as SUBMITTED for work waiting on your review') and when to use after ('to read on from the last id you saw'). It also names the alternative tool for reading a single full item: get_act.

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