tail_stream

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

With no annotations, the description carries the full burden and delivers: it discloses bounded collection, automatic termination, unsubscribing, event/time caps, and per-channel valid filter keys. It also flags a critical schema nuance ('sources' is an array unlike REST tools) and the solOnly quote-asset rejection. This is rich behavioral context beyond any structured annotation.

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?

Every sentence carries distinct information: core behavior first, termination semantics second, filter nuance third, and usage boundaries last. The length is justified by the tool's complexity, and there is 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 a 4-parameter tool with nested filter objects, no output schema, and no annotations, the description covers inputs, termination guarantees, per-channel semantics, exclusions, and when-to-use guidance. No critical operational fact is missing for an agent to invoke 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 coverage is only 25%, and the description compensates thoroughly: it enumerates valid filter keys for every channel, explains the sources array shape, and details the solOnly edge case. It also restates maxEvents/timeout semantics in behavioral terms, adding meaning beyond bare schema constraints.

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?

Description opens with a specific verb-object pair ('Collect a bounded batch of live WebSocket events') and immediately describes the terminal behavior (return and unsubscribe), distinguishing it from streaming or historical tools. It also explicitly says 'No transfers channel in v1' and contrasts with list_* tools, leaving no ambiguity about what the tool is for.

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 last sentence gives direct usage guidance: 'Use for short live watches / summaries, not history (history → list_* tools).' It also clarifies that there is no transfers channel in v1, preventing invalid calls. This explicitly routes the agent to alternatives for historical use.

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