AgentFuel

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful content beyond that — the returned fields and the newest-first ordering — but says nothing about result volume, whether entries can repeat across calls, or rate limits on a live open-world feed.

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?

A single sentence with the resource, payload, and ordering front-loaded. No filler or redundant restatement of the title.

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 simple read-only list tool with no output schema, the description does the important extra work of naming the returned fields so an agent knows what it gets. It is only slightly short of complete because it omits any note on result volume or how the open-world feed behaves.

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 limit, maxRisk, and sinceMs are already fully documented. The description only reinforces that a risk score exists (giving maxRisk meaning) and that ordering is fixed, which is marginal added value; baseline 3 applies.

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 states a specific verb+resource ('newest pump.fun token launches') and names the payload fields (creator, dev-buy share, risk score) plus ordering ('newest first'). It is clearly a discovery/list tool and is distinguishable from the sibling 'rugcheck', which is a per-token risk check, though the description never says so explicitly.

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 only implied: 'newest ... newest first' suggests scanning recent launches or monitoring new tokens. There is no explicit statement of when to prefer this over rugcheck or any other path, and no mention of prerequisites or limits on freshness.

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 establish readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely non-obvious behavior: the output is a bounded 0-100 score, it is derived from automated on-chain checks, and it carries an explicit not-financial-advice disclaimer. It stops short of mentioning latency, failure behavior for unindexed mints, or any rate limits.

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?

Two compact sentences with the return value and the checks front-loaded, followed by the disclaimer. Nothing is redundant and nothing is buried.

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 carry the return shape alone; it discloses the 0-100 score but not whether per-check flags, holder counts, or authority details come back alongside it. For a single-call, open-world lookup with full schema coverage this is adequate but leaves the agent guessing about the response payload.

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 both the mint address and the exclude list are already documented in the schema itself. The description's phrase 'holder concentration' gives indirect context for why exclude exists (pools and bonding curves distort concentration), but it adds no syntax or format detail beyond the schema. Baseline 3 applies.

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?

Names the exact artifact returned (a 0-100 risk score) plus the resource (a Solana token mint) and the two checks that drive it (mint/freeze authority, holder concentration). That is far more specific than the sibling latest_launches and lets an agent distinguish the two without reading a schema.

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 the content — call it to assess rug risk for a given mint — but the description never states when to prefer it, when it is inappropriate, or any prerequisites. With only one unrelated sibling there is no real alternative to disambiguate, so the absence is tolerable rather than damaging.

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