Read selected past report

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

With no annotations provided, the description must carry behavioral disclosure. It does reveal that reading is token-budgeted and supports offset-based continuation, which is useful. However, it does not state side effects, permissions, or that the actual schema parameter is named 'offset' rather than 'next_offset,' which undercuts transparency.

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 short sentences with the core action front-loaded and no filler. The second sentence adds useful pagination guidance, though the imprecise 'next_offset' name is a minor blemish. It is appropriately sized for a simple read tool.

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 core read behavior and token/pagination handling are present, and the output schema covers return shape. However, with no annotations, the description leaves gaps around tool-selection context, offset semantics, and when reading is appropriate versus listing or searching. It is minimally viable but not fully complete.

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 0%, so the description must compensate. It loosely maps 'token budget' to max_tokens and 'next_offset' to offset, but uses a parameter name that does not exist in the schema. report_id is only implied by 'selected report,' so the compensation is partial and somewhat misleading.

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 opens with 'Read one selected report,' giving a clear verb and object, and it distinguishes the tool from siblings like report_list and report_save by focusing on consuming a single report's contents. The phrase 'selected report' implies an existing report_id, though the resource type is not spelled out. Overall, the purpose is clear and identifiable.

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 tool's role is implied: use it when you have selected a report and want to read its content. However, it provides no explicit guidance about when to prefer report_read over report_list, daily_report_context, or research_search. The only concrete usage instruction, 'Use next_offset to continue only when necessary,' is about pagination rather than tool selection.

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