sassy_audit_false_positives

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

The annotations already mark the tool as read-only, idempotent, and non-destructive, and the description reinforces that with 'Read-only.' It adds meaningful behavioral detail beyond the annotations: the exact log file path, truncation to 120 characters, newest-last ordering, row format, and the meaning of the two event types. This gives the agent a clear picture of what executing the tool will and won't do.

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 dense but every sentence earns its place: purpose and format first, then parameter semantics, then explicit usage guidance and sibling routing. It front-loads the read-only nature and the core function before going into details, and avoids repetition of schema field names without adding context.

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?

This is a complete, self-sufficient description for a two-parameter read-only tool. It includes the data source, row format, ordering, truncation, defaults, event types, and explicit use cases. Since an output schema exists, the description need not detail return structure, and it still provides enough context for correct invocation.

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%, but the description fully compensates for both parameters. It explains count as capping rows with a default of 20, and include_bypasses as controlling whether pattern_bypass entries are included, with defaults and the effect of setting it to False. This is exactly the semantic content the bare schema lacks.

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: it 'surfaces recent shell-interceptor pattern events from the local JSONL audit log' and even gives the file path. It clearly distinguishes itself from the sibling sassy_audit_log by saying 'For general log history use sassy_audit_log.' The purpose is further sharpened with the diagnostic use cases: explaining blocked commands and picking an allow_pattern label.

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 explicitly says when to use the tool: 'Use it to diagnose why a sassy_shell command was blocked and to pick the exact allow_pattern label for a retry.' It also names the key alternative, sassy_audit_log, for general log history. Parameter guidance is embedded by explaining what include_bypasses=True vs False shows, so an agent knows how to configure the call for the two scenarios.

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