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

The description adds real context beyond the annotations: the endpoint path (POST /v1/stream/lunar-phase), the group, and the cost of 10 credits (Tier 1), which is actionable for a budget-aware agent. It does not explain what 'stream' means here (single snapshot vs. continuous push), the refresh cadence, or how billing interacts with repeated calls. There is also mild tension with readOnlyHint=false and idempotentHint=false on what reads like an informational lookup, though a billed POST endpoint plausibly explains those flags, so this is not a direct contradiction.

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 short and front-loaded: the payload statement comes first, followed by bracketed metadata lines. Nothing is padded or redundant, though the bracketed tags read as internal catalog annotations rather than natural prose.

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?

An output schema exists, so return-value shape need not be described, and parameters are fully specified in the schema. What is missing is the semantics of a 'stream' tool: whether the call opens a live feed or returns one snapshot, and how the countdown is expressed. For a tool whose defining trait is streaming, that gap is meaningful.

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 100%, with both 'fields' (dotted-path compact mode) and 'precision' (decimal rounding) fully documented in the schema. The description says nothing about either parameter, so it adds no meaning beyond the schema. Under high coverage, baseline 3 is appropriate.

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 and payload: the current lunar phase on an 8-phase scale plus a countdown to the next major phase. That is far more informative than the title. It does not, however, distinguish itself from the many similar streaming siblings (astroway_stream_ingress, astroway_stream_eclipse_incoming, astroway_stream_void_of_course, etc.), so an agent still has to infer where lunar phase fits among them.

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 when-to-use or when-not-to-use guidance, and no alternative is named. Given that many siblings are also streaming endpoints (eclipse, ingress, retrograde alerts, sunrise/sunset), an explicit routing cue such as 'use this for phase-only requests rather than the full positions stream' would materially help selection. The [Group: Real-time Streaming] tag hints at a category but does not guide choice.

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