audit_context

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

The annotations already establish readOnlyHint, idempotentHint, and destructiveHint=false, and the description reinforces that safety guarantee with 'zero text mutation.' It adds genuinely new behavioral context by disclosing the risk taxonomy (CLEAN, LOW, MODERATE, CRITICAL) and the frameworks evaluated. It does not mention throughput limits or per-profile quotas, but those live in the schema.

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 two sentences and front-loads its positioning as a pre-flight step, so the reader gets the key context first. The 'STEP 0 (Pre-Flight)' label is slightly internal jargon, but the text after it is dense and contains 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?

There is no output schema, so the description must convey what comes back. It does so by listing the categories returned (PII, secrets, severity, frameworks). The quota and profile differences are delegated to the schema, which is reasonable. The only gap is that it does not hint at the report structure or the summary-level detail.

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?

The schema description coverage is 100%, so the schema already carries the burden for 'text', 'format', 'sector', and 'profile'. The description adds the phrase 'raw prompts or document chunks,' which clarifies the intended input kind, but it says nothing about the profile, sector, or format choices. The baseline score of 3 is appropriate.

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 action ('non-destructive security inspection') on a specific resource ('raw prompts or document chunks') and enumerates exactly what it evaluates: PII, secrets, risk severity, and regulatory frameworks. It is clearly distinguishable from mutating siblings like sanitize_text and redact_file, because it states 'zero text mutation'.

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 clearly identifies when to use it: before sending content to LLMs, as a pre-flight check. It also implies a distinction from siblings by emphasizing it is non-destructive. However, it never names sanitize_text, redact_file, or guard_rag_chunk as the alternatives to use when you do want mutation or masking.

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