get_audit_tail

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint and openWorldHint, so safety and side effects are covered, and the description adds real value with 'Images are redacted' — a privacy behavior an agent could not otherwise know. However, it does not disclose ordering (newest-first?) or whether the tail is truncated, which are the remaining behavioral unknowns for a tail-read.

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 short sentences, zero filler, and the scope-and-content clause is front-loaded ahead of the redaction caveat. Every clause earns its place.

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?

An output schema exists, so return-value shape need not be explained, and the parameter is constrained by the schema. What remains missing is the ordering/truncation behavior and whether the log is global or session-scoped — minor but relevant for a read-only audit tool.

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 0%, so the description has to carry semantics for the single parameter, and 'the last n' does add meaning the schema lacks: it establishes that n counts events and that the window is the most recent ones. The bounds (1-200, default 20) are covered by the schema itself.

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 definition names the specific resource (audit-log events) and enumerates the event types it contains (tool calls, approvals, denials, e-stops), which lets an agent tell it apart from the robot-state and safety siblings. It is a noun phrase rather than a verb+resource construction, but the resource and scope are unambiguous.

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 description only defines what the tool returns; it gives no explicit when-to-use statement, no mention of when another tool (e.g. get_safety_status or get_motion_status) would be preferable, and no prerequisites. Usage is left entirely to inference from the resource name.

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