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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantial behavioral detail on top: the 2026-09-29 withdrawal, that it now emits nulls plus band_withdrawn, the enough_data flag, and the null-percentile threshold. This is exactly the extra context annotations cannot carry.

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 withdrawal notice is front-loaded, which is the most important fact, and the rest is dense but purposeful. It is a long single block with several clauses stacked together, slightly reducing scannability, but little is wasted.

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?

With no output schema, the description shoulders return-value disclosure and does so for the key fields (nulls, band_withdrawn, enough_data). It does not enumerate the full response shape, but for a withdrawn tool this is nearly complete.

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 all three enums documented, so the baseline is 3. The description adds real meaning beyond the schema by noting the band parameter is now ignored/withdrawn and that omitting every argument returns the whole table in one call.

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 names a specific statistic (median/p25/p75 seconds from first-seen curve to rug, per chain/band/window) and explicitly states its current withdrawal status and resulting behavior (returns nulls plus band_withdrawn). No sibling tool covers rug-timing percentiles, so an agent can distinguish it immediately.

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 gives a concrete use case ("how long would I have had"), the denominator definition, the 30-call threshold rule, and even the phrasing to use when data is thin. It stops short of telling the agent when NOT to bother calling a withdrawn tool or pointing to an alternative, which is the one gap.

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