list_audit_events

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description earns credit for the extras it adds: reads are non-marking, only the latest 500 events per project are retained, only verified new/resolved findings produce change events, and no external notification is sent. These are meaningful behavioral traits beyond the structured annotations, though the return shape is still unexplained.

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?

Four short sentences, front-loaded with the core action and no filler; the retention and event-trigger details each add information. Slightly sprawling, but nothing is redundant.

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 3-parameter, no-output-schema tool, the description covers pagination, retention limits, and event-generation conditions, which is a fair amount. It still leaves the return format and the meaning of limit/project_id unstated, and the after_id naming mismatch leaves a real gap in how to call it 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 0% and the description only addresses one of the three parameters, calling it 'next_after_id' while the schema declares 'after_id' — a naming mismatch that can mislead an agent about what to pass back. limit and project_id get no explanation at all, so the description fails to compensate for the zero coverage.

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 names a specific verb (read) and resource (local change/failure/recovery inbox), so an agent knows it returns audit events. It does not, however, distinguish itself from sibling audit tools such as list_project_audits, get_project_audit, or list_audit_projects, which an agent must still disambiguate on its own.

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 gives concrete continuation guidance ('Pass next_after_id on the next call') and states that events are only emitted for verified new/resolved findings, which implicitly explains when the inbox is non-empty. It never says when to prefer this tool over the sibling audit-list tools, and it uses a parameter name that does not match the schema.

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