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

Annotations already provide readOnlyHint=false, idempotentHint=true, and destructiveHint=true, and the description aligns with those by emphasizing idempotency-key reuse and transfer semantics. It adds valuable behavioral context: pending keeps a reservation, skipped/pending/failed/conversion-required sources are not confirmed ingested, and authorization is not proof of human business review. It does not explicitly describe what destructive effects may occur, but the annotations already flag destructiveness and the description does not contradict them.

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 dense but front-loaded with the core purpose and then covers constraints, alternatives, receipt interpretation, recovery, and special file-type caveats. It is longer than minimal, but every sentence adds operational guidance an agent needs; the only minor redundancy is restating the 20-file limit already present in the 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 an 8-parameter mutation tool with no output schema, this description is unusually complete: it explains the required authorization gate, payload limits, forbidden content, larger-file fallback, receipt semantics, interrupted-import recovery, non-confirmation states, and special business-library binary requirements. An agent has enough context to invoke the tool correctly and to interpret non-obvious outcomes.

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 schema description coverage at 75%, the schema already documents most parameters, but the description adds crucial constraints beyond it: combined 1 MiB limit, canonical base64/UTF-8 text, manifest-bound IDs only, no paths/URLs/authority overrides, and the recovery-key flow for resumeImportId. It does not explain versionOf or retryRejected, but those are already covered by schema descriptions, so the net contribution is strong.

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 action and resource: 'Transfer real selected source bytes after preview and user authorization.' This clearly distinguishes the tool from related siblings like helvabase_upload_original and helvabase_preview_sources by emphasizing manifest-bound, post-preview uploads. It also names workflow partners (helvabase_source_imports, resumeImportId), making the tool's role unambiguous.

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 when-to-use and when-not-to-use guidance: never send paths, URLs, guessed content, or authority overrides; use bearer-authenticated POST /mcp/files for larger payloads; use helvabase_source_imports after interruption and then resumeImportId with original bytes. It also explains which receipts mean confirmed ingestion versus pending/reservation, giving an agent clear decision rules.

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