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

Without annotations, the description carries full transparency burden. It discloses the self-healing discovery behavior, the optional application of the top result as active market ('for this session'), and the ability to surface new deployments. It does not detail error cases or authentication needs, but the core behavioral traits are well communicated.

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 two sentences: the first distills the core functionality and key differentiators (self-healing, no code changes) in a single, information-dense sentence; the second describes the optional apply behavior. Every word earns its place with no redundancy.

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 lack of an output schema and the tool's complexity (discovery with optional application), the description should clarify what the tool returns (e.g., the top subgraph details or confirmation). It mentions 'apply the top result' but does not specify return value or session persistence, leaving the agent with an incomplete picture.

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?

All three parameters have descriptions in the schema (100% coverage). The description adds value by explaining that chain and version can be omitted and that, if omitted, the highest-volume version is used. This provides practical semantics beyond the bare 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 clearly states the specific action ('Re-resolve') and resource ('best LIVE Uniswap subgraph(s) from The Graph's network subgraph, ranked by curation signal'). It distinguishes the tool from siblings like list_markets by emphasizing self-healing discovery of new deployments without code changes, making the unique purpose unmistakable.

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 context (e.g., for dynamically discovering the best subgraph) and optionally applying it as active market, but does not explicitly state when to use this tool versus alternatives like list_markets or find_pool. It lacks guidance on when not to use it or what prerequisites exist.

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 carries full burden. It mentions ranking by volume but omits behavioral traits like pagination, error handling, authentication needs, rate limits, or behavior when no pool is found.

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 concise sentences with no filler. The main purpose and input details are front-loaded, making it easy to scan.

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 tool with 4 parameters, no output schema, and no annotations, the description is incomplete. It does not explain the return format (e.g., list of pool addresses, volume details), pagination, or error scenarios, which are critical for an agent to use 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 coverage is 50% (chain and version described; tokenA and tokenB not). The description adds that tokens can be symbols or addresses, which adds value over the schema, but does not fully compensate for the missing descriptions of tokenA/tokenB.

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 verb 'Find', the resource 'Uniswap pool(s) for a token pair', and includes important details like ranking by volume and accepting symbols/addresses. It distinguishes from siblings like 'pool_info' and 'top_pools' by focusing on discovery via token pair.

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?

No explicit guidance on when to use this tool vs siblings such as 'list_markets' or 'top_pools'. It does not state prerequisites, exclusions, or typical use cases beyond the basic purpose.

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?

Explains the on-chain derivation (token price × native token USD price), providing insight into how the price is computed. No annotations exist, so description covers behavioral aspects well. Could note that price may be delayed or require specific chain state.

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 sentences, front-loaded with main purpose, no unnecessary words. Highly concise while covering key details.

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 could mention the return format (e.g., float in USD). However, the tool name and description imply a numeric price. Adequate 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?

Schema covers all three parameters with descriptions. Description adds value: explains token accepts symbol or address, chain accepts aliases, and version omission uses highest-volume. Enhances understanding beyond 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?

Clearly states it returns the current USD price of a token on Uniswap. Specifies inputs (symbol or address) and mentions the derivation method. Distinct from siblings like pool_info or list_markets.

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?

Describes accepted inputs (symbol/address, chain, optional version) and gives a sanity-check tip. Does not explicitly contrast with siblings, but the purpose is clear enough that this is the price lookup tool.

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 full burden. It discloses that the tool returns subgraph id and popularity for all available Uniswap version×chain pairs. It doesn't discuss rate limits or performance, but for a simple list with no parameters, this is sufficient.

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 sentences, no waste. The purpose is front-loaded, and every word earns its place.

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 parameters and no output schema, the description adequately conveys what is returned (subgraph id, popularity) and that it lists all. It could mention format or ordering, but it's largely complete for a simple list.

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 are zero parameters, and schema coverage is 100%. The description adds no parameter-specific meaning, but baseline is 3 for such high coverage.

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 lists every Uniswap version×chain pair with subgraph id and popularity. The verb 'list' and resource 'markets' are specific, and it distinguishes itself from siblings like 'discover_markets' by being a simple listing.

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 phrase 'Start here to see what's available' implies initial discovery usage, but it provides no explicit when-not or alternatives compared to siblings like 'discover_markets' or 'find_pool.' It lacks exclusion 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?

The description warns that TVL is flagged as unreliable, which is a useful behavioral caveat. However, with no annotations provided, it does not disclose other traits such as data staleness, rate limits, or whether the call is read-only. The one caveat is helpful but not comprehensive.

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 a single sentence that is front-loaded with the purpose ('Detailed stats') and covers key aspects without waste. It is highly concise and structured effectively.

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, the description lists expected return fields (price, volume, fees, liquidity/reserves), which is adequate for an info tool. Missing typical fields like token symbols or pair name, but 'detailed stats' implies coverage.

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 baseline is 3. The description adds context like 'by address' for the pool parameter and mentions version omission behavior, but these add marginal value 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 clearly states that it provides 'Detailed stats for one Uniswap pool/pair by address', listing key data points like price, volume, fees, and liquidity/reserves. This distinguishes it from sibling tools like 'find_pool' or 'top_pools'.

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 use when you have a specific pool address and need stats, but it does not explicitly state when to avoid this tool or suggest alternatives. For example, it doesn't mention that 'top_pools' or 'list_markets' might be better for discovery.

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 full burden. It discloses that the tool runs arbitrary queries and suggests introspection for field discovery. However, it does not mention potential risks, rate limits, authentication, or that queries may fail. The behavioral traits are moderately transparent but could be more explicit.

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 at three sentences. The first sentence immediately clarifies purpose, the second adds version-specific details, and the third provides a practical tip. No extraneous words; every sentence adds value. Well-structured and front-loaded.

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 (arbitrary GraphQL, multiple versions, optional parameters) and lack of output schema, the description covers the core idea and key hints. However, it omits details about the return format (raw GraphQL response), error handling, or any constraints. It is adequate for basic use but leaves gaps for an agent needing full context.

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 description adds meaningful context beyond the schema, such as which entities are exposed per Uniswap version (V2: pairs, swaps, tokens; V3/V4: pools, swaps, tokens) and that omitting version uses the highest-volume one. It also recommends running introspection queries, which helps the agent understand how to use the parameters effectively.

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: 'run an arbitrary GraphQL query against the resolved Uniswap subgraph for a (chain, version).' It uses specific verbs and resources, and clearly distinguishes itself from sibling tools which cover specific queries. The 'Escape hatch' label further indicates it is a fallback for custom needs.

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 implicitly indicates when to use this tool (when other tools do not cover the desired query) by calling it an 'Escape hatch'. It provides hints like running introspection queries first. However, it does not explicitly state exclusions or directly compare to siblings, leaving some ambiguity.

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 partially discloses behavior: it states results are real-time, contain USD amounts, and include the trading wallet. However, it omits details on pagination (despite the 'first' param), rate limits, caching, or whether the data is mutable.

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 sentences (23 words) with zero waste. The key information (chain scope, ordering, optional pool filter, output contents) is front-loaded and efficiently presented.

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 4 parameters and no output schema, the description covers the main purpose and core output attributes. However, it lacks explanation for the 'first' (page size) parameter and does not clarify version behavior fully (though the schema provides details). It is adequate but not exhaustive.

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 75%, but the description adds meaningful context beyond the schema: it explains that scoping to a pool is optional and that USD amounts and wallet addresses are returned. The 'first' parameter lacks a schema description, and the description does not address it, but the other parameters are well-explained.

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 uses a specific verb ('Recent swaps') and clearly identifies the resource ('on a chain') with ordering ('newest first'). It distinguishes from siblings like 'top_pools' by focusing on individual swap events rather than aggregate pool data.

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?

No explicit guidance on when to use this tool versus alternatives such as 'find_pool' or 'get_token_price'. The description implies usage for viewing recent trades but does not provide when-not or alternative tool names.

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?

Without annotations, the description carries full burden. It reveals that ranking uses volumeUSD (not TVL) and includes a TVL caveat about spam-token pricing. It also specifies return fields (pair, fee tier, volume, fees, TVL caveat). It does not mention auth needs, rate limits, or data freshness, but for a read-only query, this 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?

Two sentences: first sentence states purpose and key caveat, second lists returns. No redundant words, every sentence earns its place. Front-loaded with the most critical information (ranking by volumeUSD, not TVL).

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 description fully explains the tool's purpose, ranking logic, return fields, and a caveat. Since there is no output schema, the description adequately covers what the agent receives. With 3 parameters all documented in schema and the description adding behavioral context, it is complete for the tool's complexity.

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 good descriptions (chain aliases, first min/max/default, version options). The description adds value by explaining the ranking metric (volumeUSD), the TVL caveat, and the output fields, which supplements the schema. A 5 would require additional parameter details not in schema, but the added context is sufficient.

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 ranks Uniswap pools by lifetime volumeUSD, explicitly distinguishes from TVL-based ranking, and lists returned fields. The verb 'top' combined with 'ranked by lifetime volumeUSD' is specific and differentiates from sibling tools like pool_info or find_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 retrieving top Uniswap pools by volume on a chain. It does not explicitly state when not to use or mention alternatives, but the context is clear enough for an agent to decide. A slightly higher score would require explicit when-to-use or when-not-to-use conditions.

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