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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely useful non-schema context: the endpoint path and especially the cost note ("see your plan — endpoint not in the public credit manifest"), which an agent needs before calling. It says nothing about what a spread definition contains or how an invalid slug fails.

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?

Very short and front-loaded, with metadata compressed into bracketed lines that are easy to scan. The opening line is a fragment without a verb, which slightly weakens clarity but costs nothing in length.

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 not be explained, and annotations cover the safety profile. Still, for a lookup endpoint in a family of ~20 Marseille tarot tools, the description never clarifies the distinction from the list endpoint or what a spread definition comprises, leaving the agent to infer routing from the name alone.

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 coverage is 100%, with slug, fields (dotted-path compaction), and precision all documented in the schema itself, so the baseline of 3 applies. The description only repeats "[Required: slug]" and adds no formatting or selection guidance 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?

"Definition of a single Marseille spread" names the resource and its cardinality, which implicitly separates it from the plural sibling astroway_tarot_marseille_spreads. It is a noun phrase rather than a verb+resource statement, and the retrieval-by-slug nature only becomes explicit in the bracketed metadata.

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 statement of when to use this versus astroway_tarot_marseille_spreads (list) or the draw_* tools that actually apply a spread. The agent must infer from the name that this is a catalog lookup for one spread definition. No exclusions, prerequisites, or error cases for an unknown slug are given.

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