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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description adds substantial behavioral detail beyond them: entry is captured at the moment of logging and never backfilled, losers remain in the denominator, and results are recomputed hourly with possible 45s latency or error='recomputing' followed by instant retries. This equips agents to handle transient failures and interpret results correctly.

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 description consists of three purposeful sentences: the first front-loads the core purpose, the second adds critical methodological caveats (entry timing, denominator), and the third covers recompute timing and error behavior. Every sentence contributes unique, actionable information with no redundancy.

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 zero-parameter read-only tool with no output schema, the description thoroughly explains what the returned outcome shares represent, clarifies the population vs. track-record interpretation, and covers the recompute delay and error case. It addresses likely agent questions about interpretation and handling transient failures, leaving no material gaps.

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 has zero parameters and the schema coverage is 100%, so the baseline of 4 applies. The description naturally doesn't need to elaborate on parameters, and it effectively communicates that the tool requires no inputs, making any further detail unnecessary.

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 measures forward outcomes for PumpPill-logged tokens across both chains, specifying the exact thresholds (doubled, 5x, 10x, never moved) and clarifying the entry price definition. It distinguishes itself from a 'track record' and is distinct from all sibling tools, none of which describe outcome measurement.

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 provides clear context for when to use: to get population-level outcomes across both chains, not individual track records. It also discloses recompute timing, which guides when to call or retry, but it does not explicitly name alternative tools or provide comprehensive when-not-to-use guidance beyond the track-record exclusion.

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