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

Since no output schema exists, the description usefully discloses the return shape (per-hash upload URLs, session id, ready-made curl commands) and the operational constraint to run from the site folder with $DEEDPAGE_TOKEN. That goes well beyond the annotation set (readOnlyHint=false, destructiveHint=false, openWorldHint=true). It omits session/URL expiry and what happens if a PUT fails, which matters for a multi-step upload workflow.

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?

Front-loaded with the most decision-relevant fact—what comes back—followed by inputs, eligibility threshold, and workflow caveat. Every sentence is functional, though the enumerated input list is largely redundant against a fully documented schema.

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 9-parameter, no-output-schema tool, the description supplies the missing return contract, the size/hash preconditions, and the fact that a finalize step is still required. An agent has enough to decide whether to call it and how to proceed afterward; residual gaps (expiry, retry behavior) are secondary.

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 100%, so the schema already documents every parameter including the nested file entry shape. The description's 'Inputs:' sentence mostly restates the parameter list and the {path, sha256, size, content_type?} shape without adding semantics such as how merge interacts with expected_version. Baseline 3 applies when the schema carries the load.

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 concrete verb and resource ('accepts a file manifest and returns which hashes are already stored') and enumerates the exact return payload: upload URLs, session id, and curl commands. It also separates itself from publishing ('Does not publish by itself'), which distinguishes it from publish_site and finalize_upload.

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?

Gives a concrete activation threshold: 'Applies when the files are larger than about 4 MB, or when each sha256 is already known.' It also warns 'Does not publish by itself,' which tells the agent another step is required. It does not name the alternative sibling (publish_site for small files, finalize_upload for completion) explicitly, leaving the agent to infer it from 'the last line finalizes the upload.'

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