invariant_trace

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

No annotations are provided, so the description shoulders the full burden of behavioral disclosure. 'Trace' suggests a read-only exploration, and 'bounded' hints at limits, but it does not state whether the operation modifies state, requires permissions, or how it handles large graphs. This is a gap for a tool that inspects graph evidence.

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 concise sentence with no filler. It front-loads the main verb and resource, but packs a lot of jargon ('graph-evidenced', 'bounded local flow cone') that may reduce accessibility without expansion.

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 tool has four parameters and no output schema, and the description does not explain return values, result structure, or how the 'format' parameter alters the response. It also does not position itself against the many sibling tools in graph analysis. This leaves significant gaps for an AI agent deciding to call it.

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 only 25% (only the 'format' parameter has a description). The description mentions 'value or field' but does not explain 'value', 'depth', or 'limit' beyond the schema types, and does not clarify how the bounded local flow cone relates to these 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 uses a specific verb, 'trace,' and identifies a resource ('producers, mutators, checkers, consumers') and scope ('bounded local flow cone'). It conveys the tool's function and distinguishes it from simpler flow/query tools, although the heavy graph terminology may be opaque without context.

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?

No guidance is given on when to choose this tool over alternatives such as 'flow', 'reaches', or 'sources_of'. The phrase 'bounded local flow cone' implies a local-analysis use case, but there is no explicit when-to-use or when-not-to-use direction.

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