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

Beyond the annotations' readOnlyHint and idempotentHint, the description discloses crucial behavioral nuances: no new scan is ever triggered, found=false is an honest miss, deep=true changes which checks ran, flags are evidence-backed findings not predictions, and peak is measured since scanning began. These details meaningfully shape how the agent should interpret results.

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 is longer than average, but almost every sentence adds a needed caveat or semantic clarification. It is front-loaded with the core purpose and then layers essential interpretation rules. Slight redundancy around the stored/no-new-scan point keeps it from being maximally tight.

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?

Given there is no output schema and this tool has nuanced result semantics, the description covers the critical return-value meanings: found, deep, flag, and peak. It also addresses timing and interpretation pitfalls. An agent has enough context to invoke the tool and correctly interpret its result without additional documentation.

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 schema only says 'Address', but the description specifies the exact required format ('0x + 40 hex') and ties it to a Robinhood Chain token. With 0% schema coverage, this fully compensates for the missing schema-level documentation and gives the agent a precise validation rule.

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 opens with a specific verb and resource: 'STORED safety read for one Robinhood Chain token', then enumerates the exact data dimensions (sellability, flags, launch money, market-cap run). It is clearly distinct from siblings like rh_flagged_recent or sol_token_detail because it is address-keyed, Robinhood Chain-specific, and read-only.

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 gives clear usage context: it is a fast cached read that 'NEVER triggers a new one', so agents know it is appropriate when a stored result is acceptable. It also explains how to interpret found=false as an honest miss rather than a clean bill of health. It stops short of naming alternative tools for fresh scans or other token chains, so it lacks explicit when-not/alternatives guidance.

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