Astral Demo

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

Beyond the readOnly/idempotent/destructive annotations, the description adds important behavioral context: no network, no auth, no required input, and a clear mapping between the returned 'input' and 'chart' fields. This gives the agent a precise mental model of what will happen when invoked.

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 dense but every clause earns its place: it front-loads the purpose, gives the example details, explains the output structure, and finishes with cost/access characteristics. There is no filler or repetition.

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 zero-required-parameter demo tool with an output schema, the description is complete: it explains what the example contains, how it relates to the real compute tool, and that no network or auth is needed. Nothing essential is missing.

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% for the single optional response_format parameter, including its enum and default. The description does not need to restate that; it adds no extra parameter-level meaning, which matches the baseline 3 for fully-schema-covered parameters.

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 states a specific verb ('Return') and resource ('fully-worked example natal chart'), and explains exactly what the demo provides: a precision audit and exact payload shape. It clearly distinguishes itself from astral_compute_natal_chart by framing this as a pre-flight example rather than a real computation.

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?

It explicitly tells the agent when to use this tool: before sending real birth data, to inspect the payload shape. It also names the alternative (astral_compute_natal_chart) and explains how to use the output as a template for that call, which is strong usage guidance.

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