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

Beyond the annotations, it discloses key behavior: parsing is deterministic and LLM-free (with CPU CV/OCR for PDFs/scans), unclear spans are flagged rather than guessed, and no record is created until human review. This goes well past readOnlyHint=false and destructiveHint=false and tells the agent exactly what to expect.

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 front-loaded with the actionable instruction (paste text or drop a PDF) and then explains the parsing and review workflow. It is somewhat long and includes emphatic marketing phrases like 'ZERO LLM', but nearly every sentence contributes useful context.

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 complex ingest tool with no output schema, it explains the input paths, extraction scope, deterministic parsing, human review gate, and the fact that no transaction data is required yet. It could be slightly more complete about what the call returns or what happens between ingest and review, but the essential workflow is covered.

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 already documents all three parameters. The description still adds useful meaning by reinforcing the text-or-file_base64 alternative and clarifying that file_base64 may be a scanned document handled by OCR, which helps an agent choose the right input path.

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 states a specific verb and resource: ingesting a rebate agreement via pasted text or a PDF, then extracting customer, basis, rate/tier ladder and period with a deterministic parser. This clearly separates it from siblings like compose_agreement or receive_document, which do not describe extraction of rebate terms.

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?

It clearly places the tool in the workflow: use it to set up the agreement before any transaction data is asked for, and note that nothing is finalized until a person reviews and certifies in the browser. It does not explicitly name when to choose this over sibling tools such as receive_document or ingest, which keeps it from a 5.

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