Stream Engine Stats

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

Goes well beyond the readOnly/openWorld annotations by disclosing the exact return shape: one frame of cumulative counters with every per-second value null, versus an interval-rate frame every five seconds when the SSE Accept header is used, and that the stream never terminates on its own. That 'why are the rates null' and 'why does this call hang' information is precisely the behavioral context the annotations cannot convey, and it is consistent with readOnlyHint=true and destructiveHint=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?

Two dense sentences, front-loaded with what is read and followed by the response-shape caveats; the engine list and metric list are informative rather than padding. Slightly heavy in clause stacking ('with the settings and opt-ins that shape them'), but nothing is redundant.

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 usefully takes on the burden of explaining return values and the streaming mode, which is the hardest part of this tool. It is incomplete on the input side, however: five parameters at 0% schema coverage are left undefined, so an agent must guess env/region semantics and required-versus-optional behavior.

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% and the description names no parameter at all — env, region, workspaceSlug, appSlug and serviceName go entirely unexplained, including the enum values and whether env defaults to production. Only indirectly does 'the engine behind a compose service' hint that serviceName identifies the engine; this does not compensate for the coverage gap.

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?

States a specific verb and resource ('Reads the engine behind a compose service') and enumerates the engine types and metric families covered, so an agent knows this is engine-level statistics rather than app metrics or deploy data. It never names a sibling such as streamEngineStatements or queryAppMetrics, so the differentiation from adjacent tools is inferred rather than asserted.

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 SSE sentence gives actionable guidance on the live-follow variant ('Sending `Accept: text/event-stream` instead follows it live'), including cadence and that it never completes. There is, however, no explicit when-to-use/when-not guidance against the many sibling metric and observability tools, and no stated prerequisites beyond the implicit slugs.

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