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

The description adds genuinely useful operational context beyond the annotations (workspace settings permission required, 50-document cap, HTML pages rejected with 415, text is extracted/indexed). However, it states the call is 'Retry-safe: a repeat call with the same idempotency_key returns the original result,' which asserts idempotent behavior while the annotation declares idempotentHint=false — a direct conflict on the retry semantics an agent uses to decide whether re-calling is safe.

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?

Four dense sentences, front-loaded with purpose and source options, then constraints, then operational behavior. Each sentence carries distinct information (format limits, XOR rule, indexing target, permission/quota, retry semantics) with no filler.

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 an 11-parameter create tool with no output schema, the description covers ingestion format, constraints, permissions, quota, and error behavior well. It omits what a successful call returns (e.g., a document id to feed into aidelly_get_brain_document), the only notable gap given no output schema exists.

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 45% across 11 parameters, so the description must compensate. It contributes the mutual-exclusivity rule ('exactly one of text or source_url'), the optional title/document_type/tags, and the idempotency_key retry semantics, but leaves body, query, brand_id, description and workspace_id partly unexplained, so it only partially fills the coverage gap.

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+resource ('Add a reference document to the workspace Brain') and names both ingest paths (pasted text or source_url file). It also distinguishes itself from sibling document tools by explaining that the text is extracted and indexed for aidelly_search_brain, so an agent knows this feeds the search corpus rather than, say, the upload-URL flow.

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 when-to-use rules: 'Supply exactly one of text or source_url' and 'web pages return 415, so send their text instead,' plus the retry condition. It stops short of contrasting with the closest siblings (aidelly_add_brain_entry vs. create_brain_document_upload_url), so it doesn't reach full alternative routing.

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