security-preflight__screen_injection

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

Annotations are absent, so the description carries the full behavioral burden. It does disclose that results are heuristic indicators, not calibrated probabilities or guarantees, and that no model calls or automatic follow-on purchase occur. This is useful honesty, but it omits whether the call is read-only, whether it has side effects, what the output looks like, and why an agent_id is required. The heuristic caveat is a genuine addition, but overall disclosure is partial.

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 short and front-loads the batch scope and screening action, then adds caveats. The bracketed prefix is noise, but the core sentences are efficient and no sentence is wasted. Overall structure is good.

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?

No output schema exists, so the description should explain return values or at least the nature of the response; it does not. Combined with zero annotation coverage, zero schema description coverage for agent_id, and no sibling routing, the definition is inadequate for an agent to invoke this tool confidently in a complex security-preflight namespace.

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 must compensate. It adds only the batch size constraint (1–20 samples) and total size cap (64 KiB) for 'texts', which is genuinely helpful. However, it says nothing about 'agent_id', the other required parameter, leaving half the parameters undocumented in both schema and description.

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 ('screened for deterministic injection markers') and resource ('1–20 text samples'), distinguishing the tool as an injection-screening operation. It is fairly clear, though the prefix '[security-preflight — static manifest, source and text security checks]' is more namespace decoration than purpose. Sibling differentiation is implied by the security focus and tool name, but no sibling is explicitly named or excluded.

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?

No when-to-use or when-not-to-use guidance is provided. The agent must infer that this tool is for pre-checking untrusted text, but the description never states prerequisites, the absence of follow-on actions is only noted as 'No model calls or automatic follow-on purchase', which is a caveat rather than an alternative-selection rule. With many security-preflight siblings (scan_source, security_preflight, get_security_receipt), no routing help is given.

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