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

Annotations already cover the safety profile (read-only, idempotent, non-destructive, open-world), so the bar is lower. The description adds real value beyond them by disclaiming auth semantics: 'Address is routing input, not proof of ownership' tells the agent no credential/ownership check is required, which is not derivable from the annotations.

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?

Two short sentences with no filler, and the primary purpose plus endpoint lead the text. Tight and front-loaded; not padded.

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?

Four parameters with 0% schema coverage, no output schema, and no explanation of what the response contains or what sol/dust/chains do. For a tool whose inputs are entirely undocumented, the definition leaves too much unspecified for reliable 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 description coverage is 0% and the description only gestures at one of four parameters ('Address'). The meaning of sol, dust, and chains is left entirely unexplained, so an agent cannot tell what to pass for three of them. With zero coverage, the description needed to compensate and largely did not.

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?

Names the resource (portfolio/holdings) and grounds it in a concrete endpoint (GET /api/portfolio), so the agent knows this is a read of an address's holdings. It stops short of distinguishing itself from siblings like memeswap_token/memeswap_tokens, leaving some ambiguity about whether 'holdings' means balances, positions, or value.

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?

"Before/after a meme buy" gives a concrete usage context that an agent can act on. No alternatives or exclusions are named, so it doesn't reach the top band, but the scenario is clear rather than merely implied.

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