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

Annotations already declare readOnly, idempotent and closed-world, so the safety profile is covered. The description still adds non-obvious behavioral facts: 'No predictions, nothing stored', that birth time/place are optional, and that the celebrity path returns a score and share text.

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?

Three tight sentences, front-loaded with what the tool produces before covering the optional-input caveats and the celebrity mode. Dense but no filler; the mode-switching detail is worth its space.

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?

For a nested two-person input with no output schema, the description covers both invocation modes, optionality of birth time/place, and roughly what comes back (aspects, orbs, summary, score/share text). Minor gap: it does not describe response shape for the non-celebrity path in detail.

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%, so the schema already documents every field, its format and the latitude/longitude vs birth_place trade-off. The description only adds the person_b-vs-celebrity substitution rule, which is a modest increment over the schema's own wording.

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 ('Compares two birth charts (synastry)') and immediately names the concrete output: closest aspects between A's and B's planets with orbs and a summary. It is clearly distinguishable from siblings like get_birth_chart (single chart) and get_transits.

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?

Explains the two operating modes and the condition that selects each: pass person_b normally, or use `celebrity` instead for a playful match, with a pointer to list_celebrities. It also flags which inputs are optional, but does not explicitly state when to prefer this over get_birth_chart for a single person.

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