scan

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

No annotations are provided, so the description shoulders the burden. It discloses that results are cached per graph, explicitly returns a census of scanned/skipped entrypoints, suppressed capsules, truncated closures, and the analysis frontier, and clarifies the tool produces 'ranked questions, not verdicts.' This is substantial behavioral disclosure, though it does not mention authentication needs or possible side effects.

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 only two sentences but carries a high density of meaningful information: core operations, return restrictions, output census, caching, and parameter guidance. It is front-loaded with the primary scan and sanitization, and every clause delivers new, relevant details.

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?

The output is complex and there is no output schema, but the description gives a reasonable summary of the returned content and a cache. Still, the semantics of include_suppressions and the precise meaning of 'guard-differential talk' and 'suppressed capsules' are left to jargon without further explanation. This leaves significant work for an agent, especially with five optional parameters and no structured return schema.

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 low at 40%, so the description must compensate. It does clarify the most important parameters: entrypoint bound the initial scan, min_rank/limit page results. However, it does not provide semantic details for include_suppressions or format beyond what the schema already offers. This is partial rather than full compensation.

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 directly identifies a specific action ('Scan the graph') and a well-defined subject ('guard-differential investigation capsules'), then precisely defines those: 'entrypoints that can reach sensitive effects without a recognized dominating guard.' It also disambiguates itself by explicitly saying results are ranked questions, not verdicts, which differentiates it from sibling tools that might perform verdict-oriented analysis.

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 practical usage direction: 'use entrypoints to bound the initial scan' and 'min_rank/limit for the returned page.' It implies the tool is an investigative or triage starting point, not a final decision maker. It does not explicitly name alternatives or when-not-to-use, hence the omission from a full 5, but overall the context is clear.

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