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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new context: a 30-60 second latency expectation and the return shape (each entity with type and position). It does not mention any length limits or failure modes.

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?

Three tight sentences: purpose first, return shape second, usage trigger third. No filler, no restatement of the tool name or title, and the latency caveat is placed where it is actionable.

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?

With no output schema, the description correctly carries the return-value burden by naming entity type and position, and it adds latency. The main remaining gap is what happens to input beyond the schema's max length or how large documents should be chunked. Sufficient for a single-parameter read-only 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?

Only one parameter, and the schema documents it with no prose (coverage 0%). The description compensates by clarifying that the input is raw plain text rather than a file path, filename, or URL — a distinction that matters given the pdf_* sibling family. It does not mention the 200,000-character cap, but that is visible in the schema.

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 and resource ('Scan plain text for personally identifiable information') and enumerates the entity classes detected (names, emails, phone numbers, addresses, IDs), so the agent knows exactly what output to expect. It is clearly distinguishable from siblings like pdf_redact, pdf_extract_text, or ai_summarize.

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?

Gives an explicit triggering context: 'Use this when the user asks to check a document for personal or sensitive data before sharing it.' That is a clear when-to-use statement, but there is no when-not guidance and no routing pointer to the obvious counterpart tool (pdf_redact) for acting on the findings.

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