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

Annotations already carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is in structured data. The description adds genuinely new behavior: the return contract ('risk score (0..1), the detected intents, and whether it is suspicious'), the data-handling guarantee ('nothing stored, no tenant data'), and the auth requirement ('No token needed'). This exceeds what annotations convey.

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?

Two sentences with zero filler: the first states the core function, the second front-loads the operational facts an agent needs (cost, auth, storage, output). No sentence is redundant with the schema or annotations.

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?

For a low-complexity tool (3 params, no nested objects), the description compensates for the missing output schema by stating the result shape (score, intents, suspicious flag). It covers auth, retention, and purpose; minor omissions like rate limits or the exact JSON envelope are not critical for a read-only screening call.

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 baseline is 3. The description's 'prompt or text' phrasing maps to the required `text` parameter, and 'No token needed' clarifies why `agent` is optional, but no parameter-specific semantics are added beyond what the schema already documents.

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 opens with 'Screen a prompt or text for injection, jailbreak and exfil intent,' a specific verb+resource+purpose that clearly distinguishes this from the flocore_* siblings (tickets, tenants, queues, mesh lanes), none of which perform screening. The title 'Screen for prompt injection' reinforces the same specific purpose.

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 gives clear context for when the tool is appropriate: 'Free, public, defensive-only… No token needed' signals that it requires no credentials and is safe to invoke, which an agent needs before calling it. It does not name alternatives or explicit when-not conditions, but the sibling set is topically distinct enough that the intended use (pre-screening untrusted text) is unambiguous.

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