decision_gap_report

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

With no annotations provided, the description carries the full burden of behavioral transparency. It correctly labels the tool as 'read-only,' which is crucial. However, it does not elaborate on the specific behavioral traits: it doesn't mention if any side effects occur (e.g., caching), what the 'findings' format looks like, or whether the operation requires special permissions beyond read access. It adds some value beyond the schema but could be more transparent given the tool's analytical nature.

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 a single, clear sentence that efficiently communicates the tool's core function and output type. There is no wasted verbiage, and the key action ('Compare') and result ('return read-only attention findings') are front-loaded. Every word earns its keep.

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 has 5 parameters, no output schema, and no annotations, the description provides a solid high-level understanding. The lack of output schema means the agent cannot infer the return structure from structured data alone, but the description's 'attention findings' gives a useful conceptual summary. It is complete enough for a tool with well-named parameters and a straightforward analytical purpose, though additional examples of findings would strengthen usability.

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 60%, meaning 3 of 5 parameters have descriptions. The tool description adds high-level context ('Compare...') that ties the parameters together into a coherent purpose, but it does not explain each parameter's role in the comparison. However, 'limit,' 'window,' 'repeat_threshold,' 'expiring_soon_hours,' and 'noisy_scenario_threshold' are well-named and their purposes are largely inferable from the parameter names and the high-level description. The description adds moderate value by hinting at the parameters' roles in the comparison logic.

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 uses a specific verb ('Compare') and clearly identifies the resources being compared ('active CrowdSec decisions' vs 'recent alerts'). The output is explicitly described as 'read-only attention findings,' which distinguishes its purpose from sibling tools that modify state (like 'ban_ip' or 'allow_ip') or retrieve raw data (like 'recent_crowdsec_decisions' or 'recent_crowdsec_alerts').

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 implicitly suggests use when an agent needs to identify discrepancies between decisions and alerts. However, it does not explicitly state when NOT to use this tool (e.g., when you just need raw alerts or raw decisions) or mention alternative sibling tools for comparison. The context from sibling names helps, but the description itself lacks explicit usage guidance.

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