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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds a genuinely new behavioral trait: matching is deterministic and no external LLM is invoked. That is useful for an agent reasoning about reproducibility and latency. It still doesn't mention rate limits or input limits, so not a 5.

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, zero padding, with the action and its outputs front-loaded before the determinism caveat. Nothing is redundant with the title.

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 needn't be described, and annotations carry the safety profile. The description adequately frames the tool, with only minor gaps around input sizing and how it relates to sibling lookup tools.

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% for the single 'scenario' parameter, so the description must compensate. 'A described call or text' tells the agent the parameter is free-text narrative rather than an ID, which is modest value, but the 5000-char limit and expected level of detail are undocumented.

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 (match) and resource (a described call or text) plus the outputs produced (scam hubs, red flags, recommended verification step). This is far more specific than siblings like get_scam_stats or list_scam_types, though it stops short of explicitly naming which sibling to prefer.

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 phrase 'a described call or text', suggesting it is for case-by-case assessments, but there is no explicit when-to-use or when-not-to-use guidance. It never contrasts itself with search_incidents or explain_scam_type, so an agent must infer that this is the per-incident assessment path.

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