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

Beyond the annotations, the description discloses important behavioral traits: HMAC-SHA256 stability and linkability, same detectors as /v1/text/redact, non-detection of names and addresses, key and text never logged or stored, typical latency, price, and absence of a free tier. These details materially help an agent understand security, output, and cost characteristics.

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 front-loaded and information-dense, covering purpose, output, limitations, security, latency, and pricing. It is slightly long and repeats some title/purpose content, but most sentences carry operational value.

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?

The tool's annotations, schema, and output schema are already rich, and the description fills remaining gaps around security model, detection limits, output shape, operating constraints, and pricing. An agent has enough context to invoke it correctly and understand its limitations.

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 100%, so the parameters are already well documented. The description adds useful context about the key's HMAC-SHA256 behavior and token stability, but it does not add parameter-level syntax or constraints beyond what the schema provides.

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 ('Pseudonymise') and resource ('PII in text'), then enumerates the detected types and describes the returned token format. An agent can distinguish this from redaction or generic text processing without opening the schema.

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 clear usage context by warning that this is pseudonymisation, not anonymisation, and that the key holder can test guesses. It also notes names and street addresses are not detected. However, it does not explicitly name the sibling alternative redact_pii or state when irreversible redaction should be preferred.

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