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

Annotations already declare readOnly/idempotent/openWorld, and the description adds genuinely new behavioral facts: an underlying Jev engine with an automatic Groq-hosted LLM fallback when Jev is slow or unavailable, and a sub-4.5s latency guarantee. It omits auth requirements or rate limits, but the fallback and latency SLA are the kind of operational detail that materially affects agent planning.

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?

A single front-loaded sentence leads with the core capability and appends implementation details. It is efficient, though the 'Powered by Jev' branding and sample-endpoint pointer are marginally promotional rather than decision-relevant.

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 values (including the confidence score) need not be re-explained, and the description still names the score output. Input constraints are covered by the schema, and latency/fallback behavior is covered by the description — nothing an agent needs to call it correctly is missing.

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 schema description coverage is 100%, so the 4000-character limit and 'Text to classify' meaning are already fully documented in the schema. The description adds nothing beyond that, which is the expected baseline when the schema carries the burden.

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+resource ('flag whether text contains personally identifiable information') and enumerates what counts as PII (name plus contact details, email, phone, address, government ID, financial account), plus the confidence-score output. This distinguishes it cleanly from neighbors like spam_check, toxicity, and guard.

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?

Usage is implied by the classifier framing — pass text, get a PII verdict — but the description never says when to prefer this over sibling detectors (spam_check, toxicity, guard) or when it is inappropriate. The 'Try GET /pii-check/sample' pointer is an exploration hint, not invocation guidance.

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