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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context beyond these: 'read-only local artifact read; writes no files and uses no network,' and 'never reruns analysis.' This clarifies side effects and network usage, which are not fully covered by the annotations, making the description more informative. No contradictions found.

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 compact and well-structured. It opens with the core action, lists return contents, then gives usage context, inputs, and effects in a logical order. Every sentence adds meaningful information, with no fluff or redundancy. The 'Use:' and 'Inputs:' labels help parsing, and the length is appropriate for the tool's complexity.

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 is relatively simple (read-only artifact retrieval) and the description covers purpose, usage, return content, and side effects. The presence of an output schema reduces the need to describe return format in detail. Minor gaps include a truncated schema description for 'format' and the 'path' vs 'packetDir' wording, but these do not materially impede understanding for an 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?

All three parameters (cwd, format, packetDir) are described in the input schema (100% coverage). The description adds context that cwd and packetDir locate an existing packet, but it mentions 'path' instead of 'packetDir,' causing slight ambiguity. The 'latest' behavior is described but is not tied to a specific parameter, which could confuse an agent. Overall, the schema already carries the semantic load, and the description provides marginal additional value.

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: reads the latest Fix Packet emitted by Axint after a compile or watch run. It specifies the exact contents returned (verdict, findings, diagnostics, next steps, fix prompt) and explicitly distinguishes itself from a new analysis pass. This is a specific verb+resource combination that differentiates it from sibling tools like axint.compile or axint.repair.

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 explicit when-to-use guidance: 'use after a local compile/watch/check emitted a packet; not a new analysis pass.' This tells the agent when to invoke it and implicitly when not to, but it does not name alternative sibling tools. Providing an explicit exclusion without naming alternatives is slightly below the highest bar.

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