Source Wait

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

Annotations only state readOnly/non-destructive; the description goes well beyond them by documenting that all modes return an identical aggregate shape so the caller never branches, that subset/all modes report partial progress, that a READY web-page may carry a non-blocking advisory `warning`, and the crucial distinction between an unresolved ref raising NOT_FOUND (input error) and a resolved source landing in failed/timed_out/not_found buckets.

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?

Purpose and mode rules are front-loaded in the first two lines, and the JSON return snippet compacts a lot of information efficiently. Some density (bold emphasis, inline code, multi-clause sentences about buckets) is heavier than needed, but each sentence carries 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?

With no output schema and no annotation detail, the description fully absorbs that burden: it specifies the exact aggregate keys, per-bucket entry shape, the `ok` invariant, the partial-progress guarantee, the advisory-warning case, and the error taxonomy. An agent can interpret every return path without guessing; only timeout/interval tuning semantics remain unstated.

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 carry the burden. It does explain the accepted forms of `sources` (list or comma/JSON string) and `source` (name or ID) and implies `notebook` semantics, which is the core of the tool. However, `timeout` and `interval` are completely unaddressed in both schema and description, leaving their units and retry behavior undefined.

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 concrete verb and resource ('Wait for sources to finish processing') and immediately delineates the three operating modes (subset via `sources`, single via `source`, else all). It also points the agent at a sibling ('verify with source_read (detail="full")') for the one case where follow-up is needed, so it is not confused with source_read or source_list.

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 mode-selection rules ('waits for a subset when sources is given, a single source when source is given, else every source') are clear parameter guidance, but there is no explicit when-to-use/when-not versus alternatives such as polling with source_list or await_upload. The one sibling reference (source_read) is for verifying a warning, not for choosing between tools.

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