market_pulse_supported_assets

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral detail beyond those annotations: coverage is non-uniform across venues, spot-only and perp-only assets have different capabilities, and symbol counts are always exact even when the returned list is truncated. This gives the agent an accurate mental model of expected behavior without contradicting 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?

The first sentence delivers the core purpose, followed by a concise but necessary caveat about coverage variance, then a structured Args block. Every sentence adds information: venue semantics, search behavior, limit behavior, and exact-count guarantee. There is no filler or redundant restating of schema defaults.

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 an output schema present, the description does not need to enumerate return fields. It covers all invocation-relevant context: what the tool lists, why to call it first, venue-specific capabilities, parameter options, and exact-count behavior. The explanation of basis requiring both venues also ties into the sibling market_pulse_basis tool, making the broader tool landscape coherent. Nothing necessary for correct invocation is missing.

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%, so the description carries the full burden for all three parameters. It fully explains 'venue' with every accepted value and their meaning, 'search' as a case-insensitive substring filter with an example, and 'limit' with the note that counts remain exact regardless of truncation. This is exemplary parameter documentation in the absence of schema-level descriptions.

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 clear verb and resource: 'List which crypto assets this server can actually answer for, and on which venue.' It immediately differentiates this tool from the market_pulse_* data tools by framing it as a coverage-discovery tool, not a market data tool. The phrase 'Call this before a scan rather than discovering coverage by watching individual symbols fail' further clarifies its distinct role.

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 description explicitly states when to use it: 'Call this before a scan', and what to avoid: 'rather than discovering coverage by watching individual symbols fail'. It also provides actionable guidance on venue selection by explaining the semantics of 'both', 'spot', 'perp', 'spot_only', and 'perp_only', so an agent can choose the correct slice. This goes beyond vague context and gives a clear decision rule.

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