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

Annotations already declare readOnlyHint=true, so the description need not repeat that. The description adds critical behavioral context: that on success, it returns JSON inline or saves XLSX/CSV locally over stdio, and in HTTP mode returns safe download instructions. This explains what happens after success, which goes beyond the annotations. It does not mention failure behavior or error handling, but that is not expected given the annotations cover safety. No contradiction found.

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, front-loaded with the main purpose, and includes only essential information. It is three sentences, the first stating the purpose, the second describing behavior, and the third giving usage timing. No wasted words, and each sentence earns its place.

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 tool's moderate complexity (3 parameters, one enum, one optional parameter) and rich annotations (readOnly, openWorld, idempotent), the description covers the key behavior (state retrieval, output modes) and usage context (after timeout). It also explains the difference between stdio and HTTP for outputs, and references the output schema for returns. This is complete for an agent to invoke 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?

Schema coverage is 100%, so the schema documents all parameters. The description adds context that clarifies job_id is returned by MainBook (already in schema) but also explains the output_path and result_type in relation to stdio/HTTP modes, which adds semantic meaning beyond the schema's basic field descriptions. This is valuable for an agent to understand how to use these parameters correctly, pushing it above baseline 3.

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: to retrieve the current state of a MainBook conversion job. It specifies the resource (conversion) and the action (get state), and it distinguishes itself from siblings by mentioning 'one MainBook conversion' and providing usage after convert_bank_statement times out. This clearly separates it from list_conversions and get_balance.

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 gives explicit usage guidance: 'Use this after convert_bank_statement times out.' This tells the agent when to use this tool versus the sibling convert_bank_statement. It also mentions the output modes (stdio vs HTTP), which helps the agent understand the context. No explicit exclusions, but the timing and mode guidance is strong.

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