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

With no annotations, the description carries full burden and does exceptionally well. It discloses privacy behavior (ip_address never logged/stored/token), the fact that geo is unused, check evaluation semantics (pass/warn/fail, weighted mean, verdict cutoffs), the reserved checks, and the 5-minute token lifetime. This goes far beyond the tool name and schema.

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 well-structured with a summary, check list, scoring explanation, privacy note, and returns. It is a bit long but every section earns its place by providing differentiators and critical behavioral details. Minor redundancy exists (e.g., pass/warn/fail mentioned multiple times), but overall it is efficient and front-loaded.

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?

Given the tool's complexity (nested object parameters, no output schema, no annotations), the description is remarkably complete. It lists all return fields (trust_score, verdict, checks, recommendations, sigil_token), explains the checks, overrides, and privacy, and gives the token lifetime. It covers the essential context an agent needs to invoke the tool correctly.

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?

The description enriches schema parameters by explaining that `weights` overrides the weighted mean calculation and `thresholds` overrides verdict cutoffs. It also clarifies `ip_address` usage privacy and the fact that `geo` is unused (though geo is not in the schema, the intent is clear). Schema coverage is 80%, and the description adds meaning beyond the generic schema descriptions for weights/thresholds.

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 clearly states a specific verb+resource: 'core Sigil pre-bid call' that submits a supply path and composes checks into a trust verdict with a signed token. It explicitly lists the checks composed (ads_txt, datacenter_ip, fraud_signals, bundle_verified, etc.), distinguishing it from granular siblings like sigil_verify_ads_txt or sigil_verify_ip_type.

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 provides clear context: it positions the tool as the core pre-bid call and explains that it aggregates individual checks, implying use when a combined trust verdict is needed. However, it does not explicitly name alternatives or state when not to use this tool (e.g., when only a single check is needed), so it lacks explicit exclusions.

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