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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=true), so the bar is lower. The description adds genuine behavioral context that annotations do not cover: that recording a failure feeds into a degraded-source flag in the daily plan. It does not, however, explain any permission, overwrite, or auth requirements.

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 with the core action front-loaded and the downstream consequence second. Every sentence earns its place; nothing is padded.

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?

With no output schema, the description still covers the purpose and the notable side effect (degraded flagging). For a five-parameter mutation tool it is largely complete, though it omits guidance on when in a run to call it and how watermark interacts with outcome.

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 the schema already documents all five parameters and the outcome enum. The description clarifies that the watermark may be a timestamp or cursor and ties the failure case to the outcome/errorClass fields, but adds only marginal meaning beyond the schema. Baseline 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 states a specific verb+resource: recording how far a source has been read, including the failure case. This is clear and actionable, but it does not explicitly distinguish itself from nearby siblings like source_connect or scan_status, so an agent must infer the relationship.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named. The phrase 'failed this run' hints that this is part of a run workflow, but the agent is left to infer the timing and prerequisites on its own.

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