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

Even with readOnly/openWorld/idempotent annotations, the description adds valuable behavior: the denominator definition, the 30-call threshold, null percentiles, enough_data=false, and the requested phrasing. This goes well beyond the annotations and leaves the agent prepared for edge cases.

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 first sentence front-loads the core statistic and scope, and every sentence adds information. It is slightly dense but not padded; the threshold guidance could be tighter, but it earns its place.

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 read-only stats tool with no output schema, the description conveys units, quantiles, denominator, data-sufficiency rule, and table mode. It stops short of spelling out the exact answer shape/fields, but it is complete enough for correct invocation.

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 enums and descriptions, so baseline is a 3. The description adds the omit-every-argument aggregate mode and clarifies that arguments select one chain/band/window, which is additional parameter-level 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 clearly states the tool computes median/p25/p75 time-to-rug for coins in a risk band, scoped by chain/band/window. It is not vague, but it does not name or contrast any sibling tool (e.g. groundtruth_scan_coin), so it misses the differentiation that earns a 5.

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 says 'Use it to answer "how long would I have had"' and instructs omitting all arguments for the full table. It provides clear context but no explicit when-not-to-use or alternative routing to sibling tools.

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