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

Annotations already declare this is a non-read-only, non-destructive, closed-world write. The description adds real behavioral context beyond that: the 8 MiB decoded size cap, that a job is created immediately when tableSlug is supplied, the job/job_error failure mode, and the automatic routing/splitter fallback.

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?

Four front-loaded sentences with no padding; the core upload action and the branch condition come first. The 'Returns document identifiers and processing details' sentence is largely redundant given an output schema exists, which is the only minor inefficiency.

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 write tool with an output schema, the description covers the important unknown: the branching behavior and size limit. The main remaining gap is routing between this tool and the near-identical sibling documents.upload_file.

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 only 25%, so the description must carry weight, and it does: it explains the tableSlug branch semantics and the practical size constraint on data_base64. The project_slug conditional rule is documented in the schema rather than the description, and filename is left unelaborated, which keeps this short of a 5.

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 and resource: uploads/saves a PDF from base64 bytes, and describes the two processing paths (with/without tableSlug). However, it never distinguishes itself from the sibling tool documents.upload_file, so an agent cannot tell which upload variant to pick from the description alone.

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 tableSlug branch implicitly tells the caller when immediate extraction vs automatic routing happens, which is useful conditional guidance. But there is no explicit statement of when to choose this tool over documents.upload_file, and no prerequisites (auth, ownership) are mentioned.

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