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

Annotations already declare readOnlyHint=true and idempotentHint=true, signaling safe read-only behavior. The description adds valuable context beyond annotations: the phase is 'geocentric — no observer location is needed', which clarifies an important assumption for callers. It also explains the default-time behavior and that time without a zone is read as UTC. These details supplement the annotation-provided safety profile without contradicting it.

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 moderately long but each sentence earns its place: it front-loads the core outputs, then adds use cases, defaults, and geocentric context. The structure is logical and not redundant; while it could be tightened slightly, the information density is high and well-ordered. There is no filler, and the key facts appear early.

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?

Given the tool's complexity (returns multiple data points) and the presence of an output schema, the description sufficiently covers all necessary context: what the tool returns, how to invoke it (default time, optional timezone), and the geocentric nature that removes the need for an observer location. It also clarifies the default-to-now behavior and the UTC interpretation. No critical information is missing for an agent to call 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 description coverage is 100% – both 'time' and 'timezone' have detailed descriptions covering defaults, format, and semantics. The tool description adds minimal extra meaning beyond the schema: it reiterates time defaults and explains that timezone yields observer-local timestamps, but these are already implied in the schema descriptions. At high coverage, the baseline of 3 is appropriate; the description does not materially improve parameter comprehension beyond the schema.

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 the tool 'Report[s] the Moon phase for an instant' and enumerates specific outputs: illuminated fraction, phase name, synodic age, phase angle, and next four quarter phases. It also names the concrete user questions ('what is the moon phase tonight', 'when is the next full moon') it answers, making its purpose distinct from the sibling astronomy tools such as get_ephemeris or get_sky_position. The verb-resource pairing is specific and unambiguous.

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 description provides clear usage context: it defaults to current time, explains the timezone parameter for localized output, and emphasizes that the tool answers two common questions 'in one call without iteration', implying it is the right choice for these requests. However, it does not explicitly name alternative tools or state when NOT to use it, which would fully distinguish it from siblings. The guidance is clear but not exhaustive on exclusions.

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