list_token_trades

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

With no annotations, the description carries the full burden, and it discloses the key behaviors: this is a snapshot REST query rather than a live stream, quote assets are rejected as mint, solOnly filters to SOL-paired rows, and pagination terminates when `next` is null. It does not mention auth requirements, rate limits, or error conditions, but for a read-only list tool the most decision-relevant behaviors (paging, filtering semantics, live-vs-history) are all disclosed.

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?

Five dense sentences, each carrying a distinct concern: scope, inclusion behavior, rejected inputs + alternatives, solOnly/paging/limit guidance. Front-loaded with the core purpose and sibling differentiation. It is longer than the TDQS high example but every sentence earns its place — no filler or repetition of annotation data (there are none).

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 tool with no output schema and no annotations, the description covers the essential ground: result scope, paging protocol, param semantics, and alternative routing. The main gap is the return row shape — with no output schema, an agent must infer what a swap row contains — but the paging and filtering behavior needed to call it correctly is fully specified.

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 100%, so baseline is 3. The description still adds meaning beyond the schema: the mint param's rejection of quote assets (SOL/USDC/USDT) is a semantic constraint absent from the schema's 'Base58 mint address', and the cursor param's termination condition ('stop when `next` is null') extends the schema's paging note. It also frames source as singular and routes array-style filtering to tail_stream, reinforcing the schema's warning.

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 description opens with a specific verb+resource+scope: 'One page of recent swaps where `mint` is either swap leg' — precise about what is returned and how the result is bounded. It also distinguishes itself from tail_stream by labeling itself 'REST history, not a live tail', and states the inclusion of token↔token rows. An agent can tell exactly what this tool does and how it differs from siblings without opening schemas.

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?

Alternatives are named explicitly with the conditions that select them: quote assets should go to get_token_metadata / get_token_price, and live multi-source filtering should use tail_stream with `sources`. It also gives operational when-to guidance: paging protocol ('pass `cursor` = previous `next`; stop when `next` is null') and 'Prefer limit ≤ 20 (default) to conserve context'. Nothing is left to inference.

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