Check a message for scam red flags

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered, and an output schema exists so return shape needn't be described. The description adds genuine behavioral value by enumerating the detection categories (gift cards, crypto, remote access, one-time codes, etc.), which tells the agent what the check actually looks for. It does not say whether the result is a binary verdict, a scored risk level, or a list of matched flags, nor any limits on input length.

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 core action and scope are front-loaded in the first clause, and the long flag enumeration is dense but each item adds discriminating information rather than filler. The closing sentence about get_context is a useful pointer, though it slightly muddies which tool owns the 'company' argument. No boilerplate or hedging.

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 annotations covering safety, an output schema covering returns, and only two parameters, the definition is close to complete. The remaining hole is the role of the 'company' parameter and whether the result is a verdict versus a flag list, which is the one thing an agent would still have to discover by trial. Adequate for the tool's complexity but not airtight.

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 0%, so the description carries the full burden for two parameters. 'Text' is reasonably implied by the enumeration 'message, email, text or call script', but the required 'company' parameter is never explained as an input to this tool — it only appears obliquely inside 'get_context(company)', leaving the agent unsure whether passing company scopes the red-flag checks against that company's stated never-asks. That is a real semantic gap on an optional-but-influential parameter.

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 concrete verb ('Check') and a clearly bounded resource ('a message, email, text or call script') plus an enumerated set of red flags it detects, which is far more than a restatement of the name. It is distinguishable from siblings like bill_check and get_rules by its focus on inbound scam content. It stops short of an explicit 'this is not for X' differentiation, so a 4 rather than 5.

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 flag list — an agent can infer this is for triaging suspicious inbound communications. However, there are no exclusions (e.g. when to prefer bill_check or the case_* tools instead) and the get_context reference is framed as a companion call, not an alternative to this tool. Guidance is adequate but inferential.

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