passive_perception

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

With no annotations, the description carries the full burden of behavioral disclosure. It states what the tool returns ({score}), when the score number appears, and how it handles invalid advantage/disadvantage input with an honest refusal. It also cites the SRD rule, providing strong transparency for a calculation tool.

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 three sentences, front-loads the core formula, and succinctly covers behavior, exclusions, and conditional output. Every sentence adds value without unnecessary detail.

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 output schema exists, the description need not explain return structure in detail. It fully describes the formula, the refusal behavior for advantage/disadvantage, and the conditional absence of the score. It is complete for a stateless calculation tool.

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 adds meaning beyond the schema by explaining that perception_modifier feeds into the formula and that advantage/disadvantage trigger a refusal. Schema coverage is low (38%), and the description does not clarify generic parameters like table_policy or asserted_facts, but it sufficiently covers the tool's core domain-specific parameters.

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 what the tool does: computes Passive Perception using the SRD formula. It distinguishes itself from sibling tools (e.g., check_make, save_check) by explicitly noting that advantage/disadvantage is not part of the SRD passive formula and that passing these parameters triggers an honest refusal.

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 for when to use the formula and gives an explicit exclusion: do not pass advantage/disadvantage because the SRD defines no adjustment for passive scores. However, it does not name alternative tools for active checks or other related operations, so it falls short of full 'when/when-not/alternatives' guidance.

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