stream_publish

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

Beyond the annotations, the description discloses important behaviors: it skips non-numeric points, requires an extra install ('pip install iaiops[nats]'), formats subjects as '<subject_prefix>.tag.<metric>', and returns a dict with counters. It also explicitly frames the side effect as safe egress of already-read data, adding value beyond readOnlyHint=false.

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 front-loaded with a one-line summary, then details, args, return, and example. Each section earns its place; the example clarifies usage and the install note is essential. It is concise for the amount of information covered, with 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?

With no output schema, the description compensates fully by stating the return dict structure. It covers prerequisites, alternative tools, behavior on non-numeric data, parameters, and an example—making it complete for a 6-parameter tool with only 1 required parameter.

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 carries full responsibility. It provides meaningful explanations for all six parameters (points, subject_prefix, servers, token, tls, publisher), including defaults and the expected shape of 'points', which goes well beyond the bare schema property names.

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 clearly states 'Publish already-read normalized points to a message bus (NATS)', specifying a concrete verb, resource, and scope. It differentiates itself from siblings like stream_publish_event and historian_push by emphasizing egress of already-read numeric data and pointing to a historian sink for text/state.

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?

It explicitly tells when to use: after '*_read_many' collection, for numeric points. It names an alternative for non-numeric points ('use a historian sink for text/state') and clarifies this is not a control write. This gives strong usage context beyond what annotations convey.

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