Ingest a document into the engagement

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

With no annotations, the description carries the full safety burden and does so well: it explicitly states 'apply=false previews only and writes nothing' and 'With apply=true each item is stored with its source reference'. It also discloses the scanner's limitation (keyword/sentence-ending scan is worse than the agent's own reading) and the duplicate-title skip rule, which are not inferable from the schema.

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 main purpose, default behavior, persistence switch, and duplicate rule are contained in two front-loaded sentences, followed by a focused caveat about the text parameter. The bilingual format duplicates content, but both halves are compact and every sentence carries operational information.

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?

For a write-capable tool with 6 parameters and no output schema, it covers the important decision points: preview vs persist, path vs text, duplicate handling, and source references. The main gaps are no description of the returned preview/result format and no explicit mention of an active-engagement prerequisite, but these do not block correct invocation.

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?

All parameters already have schema descriptions (100% coverage), so the description only needs to add value. It does: it explains the path/text exclusivity, warns that pasting already-read text does not improve accuracy, and clarifies that source labels appear in the source column. That advice goes beyond the schema's declarative descriptions.

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 the core action as a specific verb+resource: 'Ingest candidates extracted from a document into the current engagement.' The 'current engagement' scope and the ingest-vs-extract action distinguish it from sibling tools such as extract_from_document and read_document without ambiguity.

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 by describing the preview default and the apply=true persistence behavior, and advises when the text parameter is or is not useful. However, it never explicitly tells an agent when to choose ingest_document over sibling tools such as extract_from_document or read_document, and it does not state prerequisites such as having an active engagement.

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