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

The description adds context beyond annotations by disclosing that the tool 'creates the deal if needed' and that file_path causes the tool to 'read and upload' the file. It does not explicitly address edge cases like providing both company_name and deal_id simultaneously, but the core behavioral traits of a write operation with deal-creation side effects are clearly conveyed, complementing the readOnlyHint=false annotation.

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 efficiently organized with a summary line, usage context, and a structured Args list. Every sentence adds functional value, and the format is scannable for an agent needing to select parameters quickly. The length is justified given the parameter count and side effects.

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 tool has 8 parameters, a mutation side effect, and a dual-mode deal targeting system. The description covers all essential aspects: main action, sequencing, parameter semantics, input constraints, and next steps. Since an output schema exists, the lack of return-value detail is acceptable. This description is self-sufficient 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?

With 0% schema description coverage, the full burden falls on the tool description, and it delivers. The Args section explains every parameter, including purpose, accepted values, and relationships (e.g., 'creates deal if new, finds existing if not,' 'alternative to file,' 'used when creating a new deal'). This goes far beyond the schema's bare names and types.

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 a specific verb and resource: 'Add a document to a deal's data room.' It also states the key side effect ('Creates the deal if needed') and explicitly frames itself as 'the primary way to get documents into Sieve,' which distinguishes it from sibling tools like sieve_dataroom and sieve_deals.

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 clear when-to-use guidance ('This is the primary way to get documents into Sieve for screening') and directs the user to call sieve_screen afterward. It also explains alternative parameter paths (company_name vs deal_id, and the one-of content source requirement), effectively covering both tool-level and parameter-level usage decisions.

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