collect-market

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

No annotations are provided, so the description carries the full burden. "Subscribe" hints at a long-running stream, but nothing is said about that being a blocking/persistent job, how it terminates (duration_seconds), reconnect behavior, rate limits, or the DLQ reporting the parameters imply. The agent is left to infer operationally significant behavior from parameter names.

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?

A single front-loaded sentence with no filler, but for a 14-parameter long-running subscription tool this is under-specification rather than concision — the brevity is achieved by omitting, not by compressing.

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 annotations, no output schema, 14 parameters at 7% coverage, and a subscription lifecycle to explain — the description is far short of what an agent needs. Partial credit only because the schema's embedded description covers the top/all_symbols rule and the collect relationship.

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 7% across 14 parameters, and the description adds nothing about any of them. The schema's own top-level text explains top/all_symbols mutual exclusivity and asset_class, but kinds, quote, use_ws, book_depth, max_symbols, poll_interval, max_reconnects, dlq_report_path and duration_seconds remain undocumented anywhere.

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 a whole slice of a venue's market" gives a verb (subscribe) and a resource, but "slice of a venue's market" is undefined jargon — an agent cannot tell what a "slice" contains without reading the schema's $defs description. It also never names its closest sibling, collect, so the distinction is only discoverable inside the schema.

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?

There is no guidance on when to use this instead of collect, universe, resolve-symbols, or markets. The one genuinely differentiating fact — that symbols come from the venue's live universe rather than being named by the caller — appears only in the schema description, not here.

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