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

Annotations already declare readOnly/openWorld=false/idempotent, and the description reinforces this with 'nothing is fetched or stored', which is meaningful corroboration for an agent deciding whether it can call this without network side effects. It stops short of stating error behavior (e.g. what happens on an invalid seed or non-existent PDA), which would earn 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?

Dense and front-loaded: the op list and input/output mapping come first, then the offline-computation caveat, then the cross-reference. The trailing enumeration of all seven swapchan_playbook workflow names is list-padding that could be trimmed to a single pointer.

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?

With no output schema, the description does the necessary work by stating what each op returns (address+bump, ATA, boolean on-curve, 8-byte discriminator). What's missing is failure modes and the address encoding conventions for an 8-parameter tool where only 'op' is required.

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 coverage is 0%, so the description must carry the burden — and it largely does, mapping parameters to ops: program+seeds (as hex strings) for pda, owner+mint[+token_program] for ata, address for on_curve, name (e.g. initialize) for anchor_disc. The remaining gap is encoding of address/owner/mint fields (base58 presumably), which is never stated.

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 a specific resource (Solana address math) and enumerates four concrete operations with input→output mappings: pda, ata, on_curve, anchor_disc. The parenthetical input hints (program + seeds, owner + mint, address, instruction name) make it unambiguous what each op does, and 'address math' clearly distinguishes it from sibling tools like resolve_name or token_info.

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?

States the execution context ('Pure, offline computation (blocktools); nothing is fetched or stored') and points to swapchan_playbook for higher-level workflows, which implies this is a low-level building block. However, it never says when to choose this over address_tool, xpub_addresses, or contract_reader — the sibling most likely to be confused with it is unmentioned.

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