read_payload_chunk

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

The description states 'payload file is automatically deleted after the last chunk is read,' which contradicts annotations (readOnlyHint=true, idempotentHint=true) that imply no side effects. This is a serious inconsistency, misleading about destructiveness.

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 concise (~150 words) with clear sections (use, iteration, args, returns). Every sentence earns its place, no redundancy, and the most important info (usage pattern) is front-loaded.

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 presence of an output schema and the complex iterative workflow, the description fully explains how to use the tool in conjunction with scan_codebase, the chunking mechanism, and the file deletion. No gaps remain.

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?

Although the schema describes parameters, the description adds critical context: project_path must match scan_codebase call and chunk_index is zero-based. It also explains the return structure, adding value beyond the schema.

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 'Read a chunk of the analysis payload produced by scan_codebase,' identifying the specific verb and resource. It distinguishes from siblings (generate_agents_md, scan_codebase) by focusing on payload retrieval.

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?

Explicit usage guidance is provided: 'Call this tool repeatedly starting at chunk_index=0, incrementing by 1 each time, until the response contains has_more=false. Concatenate all data fields.' This leaves no ambiguity about the iterative workflow.

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