Chart-grounded AI chat

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

Annotations already declare readOnly/openWorld/non-idempotent, and the description stays consistent with that. It does add real context the annotations lack: 100-credit Tier 4 pricing, 5 credits if the caller brings a provider key, and a 10-turn history cap. It says nothing about how missing chart data or provider-key failures behave.

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 front-loaded sentences, the differentiator ('positions we computed, not the model's memory') comes first, and the pricing note is appended efficiently. Minor waste: the history and language counts duplicate schema constraints.

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 values need no explanation, and pricing is covered. However, `chart` is optional while the description frames the tool as chart-grounded, leaving the agent unsure what happens on a chartless call — a meaningful gap for a 5-parameter tool with a nested object.

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 only 20%, but the nested chart object carries a long inline description covering date/time/coordinates, timezone and houseSystem rules, which the call description does not need to repeat. Of the top-level params, only persona ('four voices') gets added meaning; '10 turns' and '21 languages' merely restate maxItems and the enum, and the four persona values are never differentiated.

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: it answers a chat message using chart positions computed server-side rather than model recall of a sun sign. An agent can tell this is a free-form conversational endpoint, unlike the fixed-output astroway_ai_interpret_* siblings, though no sibling is named explicitly.

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 statement, and no alternative is named despite ~20 nearby AI tools (astroway_ai_interpret_natal, astroway_mcp_ai_explain_aspect, astroway_mcp_ai_comparison_coach). The mention of history turns, personas and languages describes mechanics, not selection criteria.

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