Source Ingest

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

Annotations already declare idempotency, non-destructiveness and open-world scope, and the description reinforces idempotency with the durable-job reuse rule. It goes further by disclosing an external runtime dependency (Poppler), explicit failure semantics for empty/error extraction, and a clear non-goals boundary. It omits auth/permission requirements and any rate or size limits.

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 core purpose, then format support, failure behavior, dedupe, and non-goals — every sentence carries information. The only cost is density: a raw line break splits the first sentence and several clauses are compressed, making it slightly harder to scan.

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?

An output schema exists, so return values need no explanation; the description instead covers the things structured fields cannot — parser dependencies, unsupported feature reporting, failure conditions, idempotent job reuse, and non-goals. For a single-parameter but operationally complex ingest tool, nothing an agent needs to call it correctly is missing.

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% and the nested request object is already documented, so the baseline is 3. The description earns a bump by explaining the source_format enum in operational terms — PDF depends on Poppler, audio means PCM16 WAV, the rest use local parsers — and by flagging unsupported OCR, table reconstruction, image pixels and speech.

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: retain original bytes and extract bounded elements with explicit source positions. The closing clause ('does not index, call a model, upload to a parser service') implicitly separates it from indexing siblings like knowledge_ingest, though no sibling is named directly.

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 useful operational context (which formats work, that PDF needs Poppler, that empty/error extraction fails) but never states when to choose this tool over content_extract, knowledge_ingest or media_acquire. Usage is implied from capability rather than an explicit when-to-use rule.

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