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 non-structured behavior: every number carries a source, and the agent is instructed to surface the stamp, the sources, and the not-advice line in its answer. That is a real output-handling contract beyond what the annotations convey.

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?

Three sentences, front-loaded with the core question the tool answers, then the data inventory, then the display contract. The phrase "every number with its source" is slightly redundant with the later "Show the ... sources" instruction, costing a little economy, but nothing is padding.

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 no explanation, and annotations cover the safety profile. The description still supplies what the schema cannot: the attribution and not-advice requirements the agent must reproduce. Freshness (hourly paragraph) is implied by "the hour's paragraph" but not stated as an update cadence, which is the only real remaining gap.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The schema is trivially complete at 100% coverage, and no competing interpretation of inputs exists.

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 resource (StockMap's Crypto today page) and enumerates exactly what it returns: Bitcoin's 24-hour move, how many coins beat it, funding, and the hour's paragraph. That is far more concrete than a restated title, and it distinguishes the tool from siblings like is_it_altseason or crypto_stocks by framing it as a today-explainer. It stops short of naming an alternative directly, so it lands at 4 rather than 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?

"Why crypto is up or down today" strongly implies the trigger question (a user asking why the market moved today), and "Market data with no call on any coin" sets a boundary against prediction/advice requests. However, there is no explicit when-not clause and no sibling is named as the alternative for adjacent needs such as altseason or per-coin views. Usage is inferable but not spelled out.

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