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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered; the description adds genuinely new context: the data is cached, the snapshot window is 15 days, and a miss returns 'none' rather than computing live. It does not disclose staleness policy or rate/availability behavior, which keeps it below a 5.

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 compact sentences, front-loaded with the core action, followed by the snapshot window and the cache-miss semantics. Nothing is redundant with the schema or annotations.

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 single-parameter cached read with an output-schema-free response, the description covers the essential behavioral facts an agent needs, including the 'none' return case. It omits what fields the summary contains and how stale the cache may be, minor gaps that keep it at 4.

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 description coverage is 100%, with the address format, base58 pattern and the 'never send a private key' warning already in the schema. The description adds no further meaning about the address parameter, so baseline 3 applies.

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?

States a specific verb and resource ('Read a cached public Solana wallet trading summary') with scope qualifiers that separate it from get_token_summary and get_top_wallets. An agent can tell immediately this is a per-wallet cached read, not a token or leaderboard query.

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?

'Does not trigger fresh analysis' clearly delimits when this tool is appropriate versus a fresh-computation path, and 'none means not cached' sets the expected response for a miss. It stops short of naming an alternative sibling to call when the cache is empty, so the agent must infer the fallback.

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