ingest_text

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

The description accurately characterizes a writing, non-destructive ingestion and adds behavioral context: raw text goes into the semantic memory path, no source file is required, and metadata is optional. ReadOnlyHint=false and destructiveHint=false are respected, with no contradiction. It could disclose what happens if the target collection does not exist, but the annotations already cover the basic safety profile.

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 short, front-loaded, and easy to scan. The only minor waste is the conceptual repetition of not needing a source file and 'rather than pointing at a file' in the same sentence, which makes it slightly less lean than it could be.

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?

It is complete enough for a fairly simple ingestion task, especially because the tool appears in a family of related tools and has an output schema. However, it lacks guidance about collection preconditions and the 'source_label' parameter, which leaves an agent to guess a necessary part of the request when it is not optional and another when it is.

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 entirely for parameter meaning, but it only mentions raw text and optional metadata. The required 'collection' parameter is not explained (e.g., must it already exist?), and 'source_label' receives no semantic explanation at all. This is a real gap for a tool with 4 parameters.

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 clearly identifies the action: ingesting raw text directly with optional metadata, and distinguishes itself from file-based ingestion by emphasizing 'without needing a source file.' It also names the key use case ('semantic memory') so an agent can separate it from sibling ingest tools without inspecting schemas.

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?

It explicitly tells the agent when to use it — for notes, pasted content, or text dictated in chat — and contrasts it with pointing at a file. It does not name the sibling tools that handle files, but the line 'rather than pointing at a file' sufficiently routes the agent toward ingest_file or ingest_directory as alternatives.

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