markets

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

No annotations are provided, so the description must carry the behavioral transparency burden. It covers input behavior (accepts URL or slug, '' browses) and output content (question, YES price, smart-whale counts, volume, days left). This is good, but it doesn't disclose any potential side effects, rate limits, or whether this is read-only (likely, but not explicit). It also doesn't specify error behavior or pagination. However, for a search tool, this level of transparency is adequate.

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 description is reasonably concise, with a clear opening sentence and structured Args section. It front-loads the primary purpose and then details parameters. Each sentence adds value. The only minor issue is that the Args section includes some redundancy (e.g., category listing values, which is also in schema as a string but not enum, so it's useful). Overall, it's well-organized and not overly verbose.

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?

Given the tool's complexity (5 optional parameters, no output schema, no annotations), the description covers the essential aspects: what it does, when to use, parameter semantics, and return fields. It lacks explicit error handling or edge cases (e.g., what happens with invalid category), but that's minor. The absence of an output schema makes the return description valuable, and it provides it. The tool is well-documented enough for an agent to call it correctly.

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 must compensate. It does: for q, it explains it accepts a URL or slug and that '' browses. For category, it lists possible values. For min_volume and min_whales, it explains they filter by USD and counts, respectively. For limit, it says 'how many markets to return (1–100)' which adds range validation. However, it doesn't clarify the default behavior for each parameter when not specified, or how they interact. The description includes all parameter meanings, but the interaction among filters is left unclear, so a baseline 3 is appropriate.

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 clearly states it searches Polymarket markets and highlights the smart whales feature, distinguishing it from siblings like wallet_overview or leaderboard. It specifies the resource (markets) and the verb (search), and mentions the unique value of tracking smart money flows. However, it could be more explicit about how it differs from market_consensus, but the emphasis on 'smart whales' and 'returns each market's question, YES price, smart-whale counts' provides good differentiation.

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 gives clear context: 'Use this to track smart money flows' and describes filtering options, which implies when to use it (when you need market data with whale activity). It doesn't explicitly mention when not to use it or alternatives, but the sibling list is available and the description's focus on whale-centric data suggests it's for a specific use case. It could improve by stating 'for general market info without whale focus, use market_consensus' but it's not misleading.

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