Review Framework Code

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

Annotations already provide readOnlyHint=true and idempotentHint=true. The description adds essential context beyond these: it explicitly states 'Does not execute or submit' (confirming read-only behavior), discloses a per-call cost ($0.001 USDC or 1000 drops XRP), and asserts 'catalog-backed, not LLM-invented' for reliability. All of this is valuable and non-redundant; there is no contradiction with the annotations.

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. The main purpose and output are front-loaded in the first sentence. Usage guidance, safety note, and cost follow logically. Every sentence earns its place; no filler or repetition.

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 moderately complex with 3 parameters and an output schema that already describes return structure. The description covers the core decision points: what it does, when to use it, that it is read-only, cost, and reliability. It appropriately routes to the main sibling tool. No missing information that an agent would need to call it correctly.

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 schema covers all 3 parameters with descriptions, so the baseline is 3. The description adds meaningful semantic value: it lists concrete dead API examples (LLMChain, initialize_agent, ServiceContext, ripple-lib) to guide the framework choice, and clarifies that 'code' is 'Source to lint before running' and explicitly 'Not a stack trace (use diagnose_framework_error)'. This goes beyond the schema's brief descriptions without being exhaustive.

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 states exactly what the tool does: scans source against known dead APIs and returns each hit with a replacement and a unified-diff hunk. It is specific about the resource (source), the action (scan), and the output. It also differentiates from the sibling diagnose_framework_error by clarifying the timing of use (before running code vs. after a stack trace).

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?

Explicitly says 'Use before running agent-written code' and points to the alternative: 'diagnose_framework_error is for after a stack trace.' This gives clear when-to-use and when-not-to-use guidance, and even names the specific sibling tool for the other scenario. No ambiguity remains.

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