Cookin

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive, so the safety profile is covered. The description adds which data fields come back (tokens, bond rate, peak market caps), but says nothing about the metered/payment behavior implied by x_payment, pagination semantics, or the cost of a call — meaningful gaps for an open-world paid endpoint.

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 compact sentence with the resource and returned fields front-loaded and no filler. Nothing in it is redundant or misplaced, even if it is on the terse side.

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?

An output schema exists, so return values need not be explained, and the four parameters are fully documented in the schema. However, for a paid, open-world, paginated tool, the description omits the payment/key prerequisite and paging expectations, leaving an agent reliant on reading the schema closely before calling.

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%, including base58 address, limit/offset paging, and the x402 payment flow, so the schema already carries parameter meaning. The description contributes no additional parameter detail, which is the baseline-3 case when the schema does the work.

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 resource and scope: the full launch history of a single token deployer, enumerating tokens, bond rate, and peak market caps. That is clearly distinct from siblings like scan_token or profile_wallet, though the description never explicitly contrasts itself with them, relying on the title to carry the 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?

There is no when-to-use guidance at all: no mention of when to prefer this over profile_wallet (which also takes a wallet address) or scan_token, and no note about prerequisites such as needing a paid x402 quote or Pro key. The agent must infer the selection criteria entirely from the name and title.

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 readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description usefully adds that results are capped at 20 with newest-first ordering, which tells an agent there is no pagination, but it says nothing about cost/auth flow (x402 payment vs. Pro key) at the description level.

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?

One sentence, front-loaded with the resource and scope, then the ordering and payload contents. Nothing is wasted and no clause needs rereading.

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 need not explain return values, and it correctly focuses on scope, ordering, and result cap. The only meaningful gap is the payment/auth model, which the schema carries but the description never hints at.

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?

There is a single optional parameter with 100% schema description coverage, and that schema fully explains the signed x402 payment and the alternative of sending a Cookin Pro key. The description adds no parameter meaning, so the schema-coverage baseline of 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?

States a concrete resource (recent buys by the top Cookin trading agents), a fixed scope (the 20 most recent, newest first), and what each record carries (quality signals, timestamp, agent attribution). It is clearly distinct from the token-centric siblings (list_new_tokens, token_trades, scan_token), though it never names or contrasts them 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: an agent can infer you call this to see what top agents have been buying. There is no explicit when-to-use, when-not-to-use, or routing to the nearest alternative such as token_trades for per-token trade data.

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 readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds nothing about the significant behavioral trait here: the x_payment parameter implies a paid x402 flow or a Cookin Pro key, yet neither cost, auth requirement, freshness/caching, nor result volume is mentioned.

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?

It is a single short fragment with no wasted words, but that terseness comes at the cost of under-specification. There is no front-loaded verb or structure telling an agent what is returned or how to call it.

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?

An output schema exists, so return values need not be explained, and annotations cover safety. Still, for a tool gated behind a payment/auth parameter, the description leaves out the one operational fact an agent most needs — how the x_payment/Pro-key step works before calling.

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 single optional x_payment parameter is fully documented in the schema itself. The description adds no further meaning about payment handling or when to omit it, which is the expected baseline when the schema does the work.

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 phrase 'Recently graduated Pump.fun tokens' names a specific resource and its lifecycle stage, which distinguishes it from siblings like list_new_tokens and list_pumping_tokens. However, it is a bare noun phrase with no verb and never explicitly contrasts itself with those siblings.

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?

There is no when-to-use guidance, no conditions or prerequisites, and no mention of the sibling tools (list_new_tokens, list_pumping_tokens, scan_token) that an agent would need to choose between. The stage word 'graduated' implies usage but does not state it.

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 readOnlyHint=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful context beyond that — results are pre-filtered for rug risk and carry 'quality signals' — but says nothing about pagination, result caps, or how the quality signals are surfaced. With annotations carrying the safety burden, a 3 is appropriate.

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 tight sentence fragment with no filler; the key qualifier ('passed Cookin's rug filters') is placed inline rather than buried. It is efficient, though the missing verb makes it read as a label rather than a statement of action.

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?

An output schema exists, so return values need not be explained, and the single parameter is fully documented in the schema. What remains thin is behavioral scope — no indication of how many tokens are returned, ranking, or recency window — but for a read-only listing tool this is close to complete.

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?

There is one optional parameter with 100% schema description coverage, so the schema fully documents the x402 payment header and the Pro-key alternative. The description adds no parameter meaning at all, which is acceptable given the schema coverage but is the baseline rather than an improvement.

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 resource ('Newly launched Pump.fun tokens') and a specific filter criterion ('passed Cookin's rug filters'), and the adjective 'newly launched' distinguishes it from siblings like list_graduated_tokens and list_pumping_tokens. It lacks an explicit verb, but the resource and scope are unambiguous enough for an agent to select it.

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: an agent can infer this is for discovering fresh launches that survived rug screening. There is no explicit when-to-use statement, no mention of when to prefer scan_token or the graduated/pumping list siblings, and no note on result freshness or limits.

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 readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered structurally. The description adds only a vague hint that results carry 'quality signals and holder behavior'; it says nothing about result volume, freshness/refresh cadence, or the payment flow implied by x_payment.

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?

It is a single short phrase with zero filler, and the distinguishing qualifier ('currently pumping') is front-loaded. Its brevity is efficient, though it borders on under-specification rather than optimal concision.

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?

An output schema exists, so return values need not be explained, and there is only one optional, fully-documented parameter. For a read-only list tool this is close to adequate, but the absence of any routing versus sibling listing tools leaves a real gap.

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% and the single x_payment parameter is fully documented in the schema, including the Cookin Pro key alternative. The description contributes no additional meaning about that parameter, so the baseline of 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 fragment 'Pump.fun tokens currently pumping' names a specific resource and a filter condition (currently pumping), which is enough for an agent to know what it returns. It does not differentiate from siblings like list_new_tokens or list_graduated_tokens, so an agent cannot tell from the text alone which listing to pick.

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?

There is no when-to-use guidance, no exclusions, and no named alternative among the several sibling list tools. The 'currently pumping' qualifier implies usage but leaves the choice between list_new_tokens, list_graduated_tokens, and list_agent_buys to inference.

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 readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds nothing beyond that — notably it never mentions that the call is metered/paid via x402 or a Cookin Pro key, which is a material behavioral fact for an agent planning a call.

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 compact clause with zero filler, and the resource plus returned fields are front-loaded. It is a sentence fragment rather than a complete statement, but nothing is wasted.

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?

An output schema exists, so return values need not be described, and both parameters are fully documented in the schema. What is missing is the access model — that a quote/payment or Pro key is required — which matters for a tool the agent may not be able to call freely.

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 base58 address format and the x_payment semantics are already documented in the schema. The description adds no meaning beyond that, which is acceptable given the high coverage baseline.

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 a specific resource ('Trading profile of one Solana wallet') and enumerates the returned metrics (PnL, ROI, win rate, bundle and smart-money flags), so an agent knows exactly what it gets. It does not explicitly contrast itself with plausible neighbors like deployer_history, but the per-wallet scope makes it distinguishable from the token-list siblings.

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?

There is no guidance on when to call this versus alternatives such as deployer_history or token_trades, nor on prerequisites (a funded x402 payment or a Pro key). The agent must infer usage entirely from the name and the schema.

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 readOnly, idempotent, non-destructive, open-world behavior, so safety is covered. The description adds the scope of what comes back, which is useful, but says nothing about cost, payment/auth requirements, rate limits, or latency for what appears to be a metered endpoint. With annotations carrying the safety profile, a 3 is right.

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 dense sentence that front-loads the resource and then lists the payload groups; nothing is wasted. It is slightly list-heavy but each element earns its place by telling the agent what is available.

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?

The output schema exists, so return structure needn't be re-explained, and the field-group list is adequately covered. However, the description omits the payment/auth mechanics that the x_payment parameter implies, leaving a material gap for a caller deciding whether this call is viable.

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 explains mint, the comma-separated fields groups, and the x_payment header alternative. The description adds no meaning beyond that, which is the baseline case when schema does the work.

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 resource and scope: a full snapshot for exactly one Solana token, and it enumerates the payload (score, holders, bundles, KOLs, cohorts, signals, ratings). That clearly separates it from the list_* siblings that operate over many tokens. It stops short of explicitly naming a contrasting sibling, so it lands at 4 rather than 5.

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?

There is no guidance on when to call this versus deployer_history, profile_wallet, or token_trades, and no mention of prerequisites. Most importantly, it never says the call is a paid x402 endpoint that requires a quote round-trip or a Pro key, which is the single most important usage fact.

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 readOnlyHint, idempotentHint, non-destructive and openWorld, so the safety profile is covered. The description adds value by disclosing the enriched per-trader fields returned, but says nothing about how many trades 'recent' covers, freshness, pagination, or that paid access via x_payment is required.

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, front-loaded with the scope ('one Solana token') and followed by the returned enrichment fields. Nothing is redundant or padded.

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 two-parameter read-only tool with full schema coverage, annotations, and an output schema, the description is largely sufficient. The only real gap is the undefined scope of 'recent' (trade count or time window), which an agent would want before calling.

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 mint and x_payment are fully documented in the schema itself. The description adds only the implicit 'one token' scoping and no additional semantics about the mint format or payment flow, so the 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 and resource ('Recent trades for one Solana token') and even names the enrichment payload (PnL, win rate, bundle membership, smart-money flag), so it is clearly distinguishable from list_* siblings. It does not explicitly contrast with scan_token or profile_wallet, which keeps it below a 5.

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 by 'for one Solana token'; there is no explicit when-to-use, when-not-to-use, or named alternative among the seven siblings. An agent must infer that this is the per-mint trade feed versus the token-level scans.

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