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

Annotations already establish that this is a read-only, idempotent, non-destructive call, so the safety burden is covered. The description goes further and discloses behaviors the annotations cannot: ordering (oldest first), sampling (one reading per period, taken on its last Friday), and automatic step-up to months then quarters beyond 160 readings. It stops short of describing error conditions or an explicit cap on total returned rows.

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?

What it returns is front-loaded correctly, and every clause carries information, but the whole definition is delivered as a single dense run-on sentence with colons and parentheticals chained together. It is efficient in length yet harder to scan than it needs to be, and phrases like 'how many times a normal Friday it was' take a second read.

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 three-parameter read tool with an output schema and full annotation coverage, the definition supplies what the structured fields cannot: ordering, period semantics, the automatic granularity step-up, and the historical start date. The one real gap is sibling differentiation, which matters here because three other tremor tools are available.

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 0%, so the description carries the full burden and largely does: weeks is bounded 1–1600 with default 52, until is typed as YYYY-MM-DD with its effect on the window, and every is enumerated as week/month/quarter with week as default. What it doesn't state is whether the automatic step-up overrides a user-supplied every, leaving a small ambiguity in a low-coverage 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?

The description states a specific verb and resource: 'The Antevo Tremor Index over time, oldest first', and enumerates the fields returned (week, level, multiplier of a normal Friday, status, strengthening/weakening split, period peak). It does not explicitly distinguish this from the sibling get_tremor_index, so an agent must infer the difference from 'over time'.

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?

Clear context is given for each parameter: weeks for how far back to go (with a default and a floor of 1997), and until for ending the period at a specific week, with a worked example ('weeks=78 with until=2009-06-30 is the 2008 crisis'). It never says when to choose this tool over get_tremor_index, get_tremor_breaks or get_tremor_pairs, so the sibling routing is left implicit.

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