ingest_preview

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

With no annotations, the description carries the full burden and does so: it declares the tool writes nothing, discloses LLM cost (~one call per 15 chunks per stage), and explains internal behavior — evidence-checking that drops unevidenced values, merging of repeated facts, and conflict detection. This is unusually rich disclosure beyond a bare verb.

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 preview-only constraint and input options are front-loaded, and every clause carries information (return contents, cost, next step). It is dense and long, but no sentence is filler — slightly heavy for a single paragraph.

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 not be re-explained; the description instead supplies exactly the missing context — safety (no writes), cost, input modes, and the handoff to ingest_apply. Nothing needed to call it correctly is absent apart from `source`.

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 0%, so the description must compensate. It covers text, path (file vs folder, .md/.txt), and exclude (skips file names), but never explains the `source` parameter (default 'text'), leaving one of four params undocumented.

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: turning mixed facts/rules/prose notes into records, with an explicit 'PREVIEW ONLY, nothing is written' scope. It clearly distinguishes itself from ingest_apply, which it names 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?

Explicitly tells the agent how to supply input ('Give text, or path — a file or folder of .md/.txt files; exclude skips file names') and prescribes the workflow: show the user summary/ambiguous/conflicts, then call ingest_apply with their answer. The alternative tool and the condition selecting it are named, not inferred.

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