mark_alerts_read

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

Annotations only give the safety booleans; the description adds real context beyond them — that it is a no-op until confirm_action, that it is reversible, and that it costs 0 credits. It also discloses the read:false inverse behavior. This is well above what the annotations convey, though rate limits aren't mentioned.

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?

A single tight sentence with the most decision-critical constraint ('PREVIEW ONLY') front-loaded. No filler.

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?

No output schema exists, and the description still covers the confirmation workflow, reversibility, and credit cost. Return format is unspecified, but for a preview-style mutation that is a minor gap.

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 is 3, but the description compounds value by tying the filters to scope ('all of them, one app's, or those up to a date') and restating the read:false inverse. It clarifies how the three optional filters combine rather than merely echoing them.

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?

States a specific verb+resource ('mark alerts as read') and enumerates the scope options: all alerts, one app's, or those up to a date. It even names the sibling confirm_action that completes the workflow, letting an agent distinguish it from list_alerts and create_alert_rule without opening a schema.

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 'PREVIEW ONLY ... Changes nothing until confirm_action' wording makes the usage context clear: this is the preview step and confirm_action is the committing step. It lacks broader when-to-use guidance (e.g., referencing list_alerts to locate alerts) but the core workflow routing is explicit.

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