Stream Engine Sessions

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

Annotations already cover the read-only, open-world, non-destructive profile, so the description is not obligated to restate safety. It adds real behavioral context instead: a required developer role, the SSE opt-in via `Accept: text/event-stream`, and the five-second frame cadence. Missing only what a non-streaming response looks like versus the streaming frame shape.

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 information and nothing is padding, but the first sentence is a 60-word chain of clauses that is hard to parse on a first read. The most operationally important facts (developer role, streaming mode) are pushed to the end rather than front-loaded.

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 does a reasonable job sketching the return content (client-grouped connections, service mapping, sessions with query text). But for a five-parameter tool with zero schema coverage, leaving every parameter undefined is a material gap an agent must resolve by guessing.

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 the full burden for five parameters, three of them required — and it says nothing about them. 'the app' and 'the compose service it comes from' faintly gesture at appSlug/serviceName, but workspaceSlug, env (the one enum), and region are completely unaddressed, leaving the agent to infer scoping from parameter names alone.

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 names a specific resource (connections grouped by client, mapped to the compose service, plus long-running/blocking sessions with query text) and clearly contrasts with the statements-oriented siblings by focusing on sessions and lock/transaction states. It is identifiable as a read tool despite the 'stream' name being explained only later. Point lost for the opening sentence being a run-on that buries the resource behind three stacked qualifiers.

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 gives one hard prerequisite ("Needs the developer role") and the diagnostic conditions it surfaces (running/blocking ≥5s, waiting on a lock), which implies when an agent would reach for it. However, it never names an alternative — streamEngineStatements, streamEngineStats, or endEngineSession — nor states when not to use it.

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