connect_onyx_docs

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

Annotations already establish that this is non-read-only, non-destructive, and idempotent. The description adds valuable context beyond annotations: it is an owner-only side effect (AC-MCP-009), requires Onyx to be running, and supports recursive directory scanning. It does not explain duplicate handling, but the idempotentHint annotation covers retry safety.

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 four concise sentences with no filler. The primary action and effect are front-loaded, followed by a capability, a prerequisite, and an access-control note. Every sentence contributes distinct 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 3-parameter ingestion tool with no output schema, the description covers purpose, accepted input types, prerequisite service state, and access control. The main omission is the expected return payload or success signal, which an agent may need to confirm the indexing operation succeeded, but annotations and schema carry most of the call semantics.

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 100%, so the baseline is 3. The description adds meaning by specifying accepted file extensions (PDF, Markdown, JSON, TXT) and recursive directory scanning, which enriches doc_paths beyond the schema's generic 'file or directory paths' phrasing. It also reinforces owner_token's purpose through 'Owner-only side effect.'

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 names a specific verb ('Index'), a specific resource ('local research documents'), and a specific target ('Onyx RAG knowledge base'). It also states the observable consequence—documents become searchable via onyx_ask() and onyx_search()—which distinguishes it from the many sibling read/query tools.

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?

The intended scenario is clear: index local research documents so they become searchable in Onyx. It also gives a necessary precondition ('Requires Onyx to be running at ONYX_API_URL'). However, it does not explicitly contrast with sibling ingestion tools like ingest_csv_data or ingest_json_signals, so it stops short of full when-to-use versus when-not-to-use guidance.

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