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

Annotations declare readOnlyHint=true, so the description is not expected to repeat safety. It adds valuable behavioral context: records persist across turns (avoiding duplicate fetches) and reading brings content into context. This is beyond the annotation and aligns with read-only semantics. No contradictions; the description supports the readOnly hint.

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 two sentences, front-loaded with the core purpose and then a practical tip. Every sentence adds value—no filler, no redundancy. It is concise and well-structured.

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 comprehensive schema (covering edge cases and URL restrictions), the readOnly annotation, and the absence of an output schema, the description covers all necessary context. It explains persistence, context loading, and line-range usage. Nothing critical is missing for correct invocation.

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 100%, with detailed per-property explanations (id format, from/to defaults, clipping, QUOTE_OUT_OF_BOUNDS, version pinning). The description's mention of line ranges adds minimal semantics beyond the schema, as the schema already covers these behaviors. Baseline 3 applies since the schema carries the parameter documentation load.

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 the tool's purpose: 'Read collected records in full, or just the line ranges you need.' It identifies the specific verb (read) and resource (collected records), and the ability to scope to line ranges distinguishes it from search (grep) or fetching (advanced_web_fetch) siblings. The phrase 'Records persist across turns' further clarifies that this reads stored data, not new content.

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 provides practical usage guidance: 'Pass line ranges to bring only the relevant parts into context instead of an entire thread or transcript.' This tells the agent when to use line ranges for efficiency. However, it does not explicitly name alternative tools or state when to choose this over siblings like grep_collected_records or ask_collected_records; such comparison is left to inference.

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