mindbase_ingest_file

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

No annotations exist, so the description carries the full burden of behavior disclosure. It does this well by stating that it archives the original into sources/raw/<date>/, uses pdfjs locally with no API call, writes an .extracted.md sidecar for PDFs, returns the text, and downloads URLs first.

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?

Three sentences of dense, high-value content. No filler, the main behavior appears first, and follow-up instructions are appended at the end in a natural order.

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?

Even without an output schema, the description tells the caller that the text is returned. It documents postconditions, input types, sidecar creation, and the recommended follow-up. For a file ingestion tool, this is complete.

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?

Input schema covers 100% of parameters with descriptions, so the baseline is high. The description adds important semantics for the required path parameter: it can be an absolute local path or direct http(s) URL, and describes the download-first behavior. Title and projectId semantics are already adequately documented in the schema.

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?

Description uses specific verb 'Ingest' with clear resource types ('file into a project'), enumerates supported types and formats (PDF, .md, .txt), and describes the concrete workflow: archive, extract, sidecar, return text. It is easily distinguishable from sibling tool names like ingest_source or ingest_plan.

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?

Clear context is provided for when to use this tool: you can pass a local absolute path or a direct http(s) URL pointing to a PDF/.md/.txt file. It also prescribes the follow-up workflow (discuss takeaways and use mindbase_contribute), but it does not explicitly state when to prefer this over sibling tools such as ingest_source. No exclusions are stated but they are not needed for basic usage.

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