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

Annotations already declare readOnlyHint=true and idempotentHint=false, so the safety profile is covered. The description adds the cursor-pagination behavior ('use next_offset from the previous call'), which is genuinely useful, but says nothing about return shape, whether the offset is stable across edits, or size caveats beyond the schema.

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?

A single well-formed sentence with the primary action front-loaded and the usage cue trailing. No padding; the parenthetical clarifies the windowing mechanism compactly.

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?

For a 5-param read tool with no output schema, the description conveys the chunking model and the follow-up trigger. It hints at a returned next_offset without spelling out the response, but combined with the schema hints that is adequate.

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 coverage is 100%, so defaults (limit 50000/max 200000, field default 'body') and enum-like values are already documented. The description's 'character windows' framing reinforces offset/limit intent but adds no syntax or semantics beyond the schema. Baseline 3 applies.

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?

States a specific verb (Read) and resource (a problem field or solution body), plus the mechanism (character windows / piece by piece). It implicitly distinguishes itself from get_problem by being the follow-up retrieval tool, though it doesn't name siblings explicitly.

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?

Gives a clear triggering condition: 'e.g. after get_problem clipped it.' That tells the agent exactly when to reach for this tool and names the upstream sibling. No explicit when-not guidance or note on simultaneous vs. sequential calls, but the context is clear.

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