collect

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

With no annotations at all, the description carries the full burden and delivers almost nothing: it does not say whether the call blocks indefinitely, what max_reconnects=-1 implies, whether records are appended vs overwritten in the lake, or that a dead-letter report is produced. Only the vague "write every record" hints at durability semantics.

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?

One front-loaded sentence with no filler and no repetition — structurally clean. But for a 7-parameter, long-running streaming ingest it is under-specified rather than genuinely concise, so efficiency alone doesn't earn a 4.

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?

No output schema, no annotations, 7 parameters including a blocking duration and reconnect cap, yet the description is a single clause. An agent can guess this streams data into storage but lacks the termination, failure, and write-target semantics needed to call it correctly.

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 14% and the three required parameters (sources, symbols, channels) are completely undocumented — notably 'channels', which likely maps to the catalog-channels/list_data_channels siblings but is never explained. The tool description adds no parameter meaning; only asset_class has schema text, and the long $defs note is design rationale rather than usage guidance.

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?

"Subscribe to live venues and write every record into the lake" gives a clear verb (subscribe) plus the two resources (live venue streams, the lake). It is a coherent ingest-and-persist statement, but it never disambiguates from the near-identical sibling 'collect-market', nor from 'backfill'/'replay' which also write into the lake.

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?

No when-to-use, when-not-to-use, or alternative is named despite obvious siblings (collect-market, backfill, replay). An agent has no stated condition for choosing this over them, or for whether it is a blocking/long-running call that needs duration_seconds set.

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