pump.fun launch feed + trend radar

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

Annotations already declare readOnly/openWorld/idempotent=false, and the description adds genuinely non-obvious behavior beyond them: ingestion latency of about a minute, a concrete price of $0.005 per call via x402, and the conditional nature of the trend fields (present only on a name match). It also sets negative scope explicitly, which prevents the agent from treating results as endorsements.

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?

Front-loaded with the verb and resource, followed by two short constraint sentences that earn their place (scope disclaimer, price). The opening sentence is long and clause-heavy—creator wallet, launch count, and match semantics are compressed into one breath—but nothing is redundant.

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 burden of return-value disclosure and does it: it names each returned field, notes that trend data is conditional and carries a source and score, and states freshness and cost. For a read-only filtered list with full schema coverage, nothing an agent needs before calling 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 coverage is 100%, so the schema already documents all four parameters with defaults and bounds; the baseline applies. The description adds modest value by explaining that trend matching is name-based and conditional, which clarifies what trendOnly actually filters on, but it adds nothing about limit, creator, or minutes beyond the schema.

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 and resource ('Lists pump.fun token launches from the last N minutes') and enumerates exactly what comes back (creator wallet, seven-day launch count, optional trend match with source and score). It doesn't name the closest sibling, trending_topics, so the agent must infer the boundary, but the 'launch data only' framing plus trend latency signals that this is a launch feed, not a raw trends feed.

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?

Usage is implied rather than stated: the freshness guarantee ('decoded from Solana mainnet within about a minute') tells the agent when this data is appropriate, and 'Launch data only; it does not rate, recommend or trade anything' scopes intent. However, there is no explicit when-to-use guidance and no exclusion pointing to trending_topics for queries that only need the trend side.

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

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

Annotations already declare read-only, open-world, non-destructive behavior. The description adds materially useful context beyond that: polling every five minutes, a per-call price of $0.01 USDC via x402, merge-by-topic ordering, and the exact fields returned. It stops short of describing payment failure behavior or rate limits, so it is strong but not exhaustive.

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 front-loaded with purpose, then output shape, then logistics, and every clause carries information. It is a single dense sentence with a long comma-separated list, which is efficient but slightly heavy to parse in one pass.

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?

There is no output schema, so the description must explain return values, and it does: score, velocity, first/last seen, type label, underlying headlines or market numbers, and pump.fun match count. Combined with the polling cadence and pricing model, an agent has enough context to call this 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 100%, so the schema already documents hours, limit, source, and minScore. The description reinforces 'strongest first' and the merged-source behavior but adds no syntax, defaults, or edge-case guidance beyond the schema.

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 names a specific verb and resource (lists trending topics) and immediately scopes it to Google Trends and Polymarket. It also distinguishes the merged, cross-source nature from any single-source alternative, so an agent knows exactly what this tool returns.

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?

Usage is implied by 'right now' and the five-minute polling cadence, which tells the agent the data is fresh but not real-time. However, the description never states when to choose this over alternatives (such as recent_launches for pump.fun activity) or when not to use it, leaving routing to inference.

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