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

ReadOnlyHint and destructiveHint already cover safety, and the description adds genuinely useful behavioral context: deterministic output, date-based selection, and teaser-scoped returns. However, the claim that all users see the same crystal is muddied by the seed parameter, which is described in the schema as an optional user identif rather than a date, and no output shape is described despite the absence of an output schema.

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?

Four sentences, front-loaded with the core purpose and followed by the important routing advice to the detail endpoint. No schema fields are restated; the 'Perfect for...' sentence is mildly promotion but still gives an agent useful signal about intended integrations.

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 low-risk read-only daily teaser tool with zero required parameters and strong schema descriptions, the description is largely complete: it explains what the tool returns, why an agent would choose it, and where to go for richer details. The remaining gap is the seed/date determinism nuance, combined with no mention of the expected teasp response shape, which would help since there is no output schema.

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%, and the schema already documents date, lang, seed, and compact thoroughly, so the description does not need to repeat them. The description's only parameter-related phrase, 'or a provided seed date,' is slightly ambiguous because seed and date are separate parameters in the schema, offering no real added meaning.

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 opens with a clear verb and resource: 'Get the crystal of the day as a discovery teaser.' It explains deterministic date-based behavior and explicitly points to the /crystals/{id} detail endpoint when full healing properties are needed, distinguishing this tool from related crystal lookup siblings.

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 gives concrete use contexts: daily guidance features, push notifications, wellness app widgets, and crystal journal integrations. It also tells the agent to use /crystals/{id} when complete spiritual, emotional, and physical healing properties are required, which is a clear not-this-tool signal, even though it does not mention every sibling by name.

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