get_document

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

With no annotations supplied the description carries the full burden, and it does disclose meaningful traits: it is a read/fetch, results are not persisted into DecisionPen, MCP itself never Confirmed-writes, and text is returned only "when extractable." It omits other behavioral facts an agent would want — permission/auth expectations, behavior on a missing or non-allowlisted key, and any size limits — leaving real gaps for a zero-annotation tool.

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-loads the action and the return shape, then covers non-persistence and the two parameters compactly. The terse "mode=cite_only|propose|persist_approved" shorthand is slightly cryptic but earns its place by ruling out writes.

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?

Two parameters, both explained, and an output schema exists so return values need not be spelled out. The one substantive gap is failure/permission behavior, which matters more here because no annotations cover it.

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 0%, so the description must compensate, and it does explain both parameters: item_id is the full S3 object key with its provenance, and include_text is a boolean that triggers extraction for cite-only use. It adds real meaning beyond the bare schema titles, though it could clarify the default (schema says true) and what happens when extraction fails.

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: "Fetch one object from the allowlisted S3 prefix." The parenthetical noting item_id comes from list_sources / search_docs implicitly separates this single-object fetch from those listing/search siblings, though it never states the contrast 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 clear operational context: use it with a key obtained from list_sources or search_docs, and set include_text when the text is needed for cite-only use. It offers no explicit "when not to use this" or routing to a sibling for bulk fetches, so it stops short of full alternative guidance.

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