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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description only needs additive context — and it delivers: the chain set is data-driven and picks up new chains the same day via get_chain_coverage, and unknown values produce a named error rather than a schema rejection. It omits pagination behavior for the cursor and what the response looks like, which is why it isn't 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 sentences, front-loaded with the core purpose, then modes, then chain-set behavior. The third sentence is long but every clause (self-updating chain list, short slugs, named error instead of schema rejection) carries non-obvious information an agent would otherwise discover only by failing.

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 7-parameter, zero-required, nested-object tool with no output schema and 14% schema coverage, the description should cover the remaining knobs. It handles chain and the top-level modes well, but cursor paging semantics, the status enum's effect, and token_address are unaddressed, leaving an agent to guess how to paginate and how to scope to a specific contract.

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 only 14% across 7 parameters, so the description must carry weight. It meaningfully explains chain (accepts any live slug, errors on unknown), and implicitly covers recent/symbol/counterparty via the mode list. But status, cursor, and token_address get no explanation anywhere, leaving a real gap.

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 first sentence names a specific resource and verb ('Cross-chain bridge transfers from the transfers pipeline') and enumerates the three access modes (network-wide recent, by token, by counterparty). That scope distinguishes it from siblings like get_address_crosschain or get_crosschain_stats without needing to name them. It stops short of an explicit sibling contrast, keeping it at 4 rather than 5.

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 mode list ('recent network-wide, by token, or by a counterparty on a foreign chain') gives an agent a clear selection rule for which parameters to combine. It also routes to get_chain_coverage for discovering valid chains. No exclusions or negative guidance (e.g. when to prefer get_address_crosschain instead) are stated.

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