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

Annotations already cover readOnly and openWorld, but the description adds substantial behavior the schema does not convey: it embeds the entire token_risk check, returns a swapUrl and a `display` markdown block containing images that must be shown, and includes prescriptive post-call agent actions. No rate limits, caching, or freshness caveats are given for a live multi-source lookup, keeping this 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?

The core capability is front-loaded and dense, but the text bundles capability description, agent directives, output-rendering instructions, and a trailing list of seven playbook workflow names that most agents will not need inline. The trailing 'How to combine this with the other tools' sentence and the workflow enumeration dilute focus.

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 carries the return-value burden well: it lists returned fields, the swapUrl, and the `display` markdown. Combined with readOnly/openWorld annotations, an agent knows the safety profile and what comes back. It lacks any note on partial/failure results (e.g. token not found or unsupported chain) for a multi-chain lookup.

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 50%: chainId carries a full enumeration of ids and names, while `address` (min 32/max 64 chars) is undocumented. The description only implies the address is a token contract/mint by saying the tool works on 'an EVM chain or Solana' and mentions Solana mint/freeze authority — it does not clarify that `address` is the token contract rather than a wallet, which is the one ambiguity the schema leaves open.

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 resource and scope — 'Everything about one token on an EVM chain or Solana' — then enumerates exactly which fields are returned (supply, price/FDV, holders, mint/freeze authority, deploy date, tax/proxy/mintable flags). It also distinguishes itself from the sibling token_risk by noting the full risk check is included, so an agent can tell which of the two to call.

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?

Gives clear operating context: always surface the risk level and flags, then offer a SwapChan swap via get_quote or the returned swapUrl, and show the `display` markdown. It also points to swapchan_playbook for multi-tool workflows. It stops short of stating when *not* to use this (e.g. call token_risk alone for a risk-only query), so no explicit exclusions.

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