poolproof — checks before you commit money

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

With no annotations, the description takes on transparency duties. It discloses that output is 'Facts and flags only, never advice', which sets expectations for output tone. It also reveals cost/rate-limit behavior. However, it does not describe what 'flags' means, how errors are handled, or the exact response structure.

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 compact and front-loaded with the core purpose. The pricing/limit info is useful context and not excessive. Slight lack of structural clarity (all in one run-on sentence) but overall efficient.

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 tool is simple (one parameter, no output schema). The description covers the main purpose, output philosophy, and access limits. However, without an output schema, it would benefit from a brief note on expected response format or example values, which is a moderate 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?

The single parameter 'chain' is fully described in the schema as 'Chain name as used by DefiLlama', giving 100% schema coverage. The description adds no further parameter details, so it meets the baseline but does not exceed it.

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 indicates the tool checks chain liveness via TVL trends over multiple periods ('Is this chain alive: TVL trend over 1y/6m/90d/30d'). This distinct purpose separates it from siblings like exit_cost or pool. The phrasing is slightly informal, but the verb+resource is identifiable.

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 provides practical usage context: free tier rate limits, shared quota with website, and paid access via x402. However, it does not explicitly state when to use this tool versus alternatives, nor does it mention scenarios where it should not be used.

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?

No annotations are provided, so the description fully carries the behavioral transparency burden. It discloses that the tool returns facts and flags only, never advice, and reveals rate limits (3 calls/hour free) and pricing for unlimited access. It also indicates the methodology (live route) but doesn't explicitly confirm it's read-only or describe error behavior.

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 compact and front-loaded with the core purpose, then adds important behavioral facts. It includes pricing and endpoint details, which are useful but could be seen as slightly dense. Still, every sentence serves a purpose, and it's under four sentences.

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 tool with no output schema, the description covers the main functionality, pricing, and usage limits. It doesn't describe the return format or specifics of 'flags', but given the simplicity and lack of output schema, it's reasonably complete for an AI agent to understand what the tool does and when to use it.

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?

The input schema already describes both parameters fairly well (mint address and size in whole tokens). The description adds emphasis on 'AT YOUR SIZE' but doesn't introduce new parameter details, format, or constraints beyond what the schema provides. With 100% schema description coverage, the 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 the tool's function: calculating the real cost of exiting a Solana position at the user's specific size, using live routing rather than theoretical slippage. It effectively distinguishes itself from potential alternatives by emphasizing 'live route, not theoretical slippage' and is specific about the resource (Solana position).

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 provides context on when to use the tool: for factual real-world exit cost estimates rather than theoretical ones, and explicitly says it provides facts and flags, never advice. It also includes usage restrictions (free tier limits, paid access) but does not name alternative tools or explicit exclusion criteria. Sibling tools offer no guidance, but the purpose gives enough context.

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?

With no annotations provided, the description carries the full burden. It discloses rate limits ('3 calls per hour per IP'), pricing ('$0.020 per call'), and the nature of the content ('Facts and flags only, never advice'). These are useful behavioral traits beyond a simple lookup.

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 concise and front-loaded with the purpose. The first sentence is long but informative, followed by a short limitation statement and practical pricing information. Every sentence has value, except perhaps the list of examples could be trimmed, but it helps clarify the tool's scope.

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 no output schema or annotations, the description provides sufficient context: purpose, example use cases, limitations, and usage costs. It does not explicitly state return format, but 'Facts and flags' hints at the output nature. Overall, it is complete enough for a simple lookup tool.

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?

The schema already describes the single parameter 'q' with high coverage. The description adds extra meaning by mentioning 'role' as an accepted input type (not in schema) and provides examples of research topics (dead redemption bridges, ticker collisions), which clarifies what kind of queries are expected.

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 the tool's purpose: to check if a research note exists on an asset, protocol, chain, or role. It uses a specific verb ('Do we hold a research note') and resource, and distinguishes itself from siblings by emphasizing qualitative insights that price/TVL data do not provide.

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 implies when to use the tool (for qualitative research notes, not price/TVL data) and includes a limitation ('Facts and flags only, never advice'). However, it does not explicitly name alternatives or state when NOT to use it compared to sibling tools like chain, exit_cost, launch, or pool.

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?

With no annotations, the description carries the transparency burden. It discloses that the tool provides 'facts and flags only, never advice' and includes rate limit and pricing details, which are behavioral traits. However, it does not mention error handling, data availability, or read-only nature beyond what is implied, leaving some gaps.

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 well-structured, starting with the core purpose, then output details, and finally pricing. It is somewhat long due to pricing specifics, but each sentence adds value. The length is justified by providing essential usage constraints without becoming unwieldy.

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 there is no output schema, the description adequately explains the return values (launch count, graduation record, creator bought own bonding curve). It also provides operational context (rate limits, pricing). While more detail could be given about the response structure, the description is sufficient for a single-parameter tool with a clear purpose.

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?

The schema already describes the 'mint' parameter fully as 'Solana mint address of the pump.fun token' (100% coverage). The description does not add further meaning to the parameter, so the baseline of 3 is appropriate, as the schema carries the semantic load.

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 the tool's purpose: to identify who launched a pump.fun token and their history. It specifies key outputs (launch count, graduation record, creator bought own bonding curve), directly distinguishing it from sibling tools that analyze other aspects like chain, exit cost, known, or pool.

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 implies usage for investigating token launch history but does not explicitly contrast with alternatives or state when not to use. The context is clear, but it lacks specific exclusion criteria or references to sibling tools, stopping at implied usage rather than providing explicit guidance.

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?

With no annotations, the description carries the full burden. It discloses rate limits (3 calls/hour free), paid tier pricing ($0.010/call), data retention (history non-reconstructable), and the advisory boundary ('Facts and flags only, never advice'). It does not describe the response format, but this is partially handled by the schema's next_since field.

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 information-dense but efficient: it opens with purpose, then covers incremental polling, data persistence, advisory nature, and pricing in four short sentences. Every sentence earns its place with no redundancy or fluff.

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 no output schema and no annotations, the description provides sufficient context for a feed tool with three optional parameters. It covers purpose, usage, constraints, and data context, though it leaves the exact response shape unspecified—mitigated by the field descriptions and next_since behavior in the schema.

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%, with each parameter (only, limit, since) already having a descriptive explanation. The description adds no new parameter-level semantics beyond reinforcing ?since= polling, matching the baseline expected when the schema fully documents parameters.

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 the tool provides a live feed of pump.fun launches from the last 24 hours with specific creator context (who deployed, prior launches, own-curve purchase). It distinguishes itself from sibling tools like 'launch' (singular) by emphasizing the feed/polling nature and the 24-hour scope.

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 explicit polling guidance ('Poll with ?since= for only what is new') and warns that history cannot be reconstructed afterwards, implying real-time use. It doesn't explicitly name alternatives or exclusion cases, but the context is clear enough for an agent to decide when to use 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'Facts and flags only, never advice', which clarifies non-advisory behavior. It also discloses access limits (free tier: 3 calls per hour per IP, shared with the website; paid tier costs $0.005 per call), which is useful operational context. It does not detail return format or data freshness, but the disclosed behaviors go beyond basic expectations.

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 the core purpose, followed by a key behavioral note and access/pricing information. It is concise, though the pricing sentence is somewhat dense and could be separated. Every sentence serves a purpose, and the structure is logical, earning a 4 rather than 5 due to the slightly cluttered pricing detail.

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 tool with one parameter and no output schema, the description provides sufficient context to understand what the tool does, how to access it, and its behavioral boundaries. It does not define every metric (e.g., 'exit depth'), but the overall purpose and usage context are clear. It is complete enough without needing an output schema.

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?

The schema covers the single parameter 'pool' with a clear description (DefiLlama pool id uuid, sourced from a specific URL), giving 100% coverage. The tool description does not add any additional parameter semantics beyond what the schema already provides, so a baseline score of 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 identifies the tool as providing yield pool safety analysis, listing specific aspects (peg, yield sustainability, emission dependence, exit depth). While there is no explicit verb like 'analyze' or 'evaluate', the noun phrase 'Yield pool safety' concisely conveys the tool's purpose. It distinguishes itself from sibling tools that likely cover chain info, exit cost, known issues, and launch, so the purpose is distinct and clear.

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 implies when to use the tool: when you need safety facts and flags for a yield pool. However, it does not explicitly state exclusions or alternatives. There is no mention of 'use this instead of X when...', so the guidance is only implied, not explicit.

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