athena_gap_compile

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 disclosure. It discloses conditional persistence ('optionally persist'), the nature of the computation ('witnessed directed reachability closure'), and that it is 'navigation closure, not logical/causal entailment.' It could go further by describing return values or side effects, but it reveals the core behavioral traits.

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 dense sentences include the core formula, a semantic exclusion, and a routing hint. Every phrase adds value, and the description is front-loaded with the most important information. There is zero filler or redundancy.

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 complexity of this tool (7 parameters, nested objects, no output schema, no annotations), the description provides a good algorithmic definition but omits practical details: what does it return? What exactly does 'persist' do? How should sources and targets be structured beyond minimal schema hints? It is adequate for domain experts but incomplete for a generic agent.

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%, so the description is the only source of parameter meaning. It maps 'frozen source groups' to sources, 'typed graph edges' to edges, 'explicit target nodes' to targets, and 'policy' to the traversal policy, plus 'optionally persist' to the persist boolean. However, it does not explain task_ref or actor, and it lacks structural details for complex params like sources and targets.

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 defines what the tool does: 'Compile and optionally persist GAP.1' with an explicit formula ('explicit target nodes minus witnessed directed reachability closure over frozen source groups and typed graph edges'). It also distinguishes itself from other tools by stating 'This is navigation closure, not logical/causal entailment,' which separates it from causal siblings.

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 usage context by explicitly stating what it is not for ('not logical/causal entailment') and hints at follow-up behavior ('Unknown residual metrics route to measurement'). However, it does not explicitly name alternative tools or provide a clear 'when to use this tool' scenario.

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