Epsilon

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is established. The description adds useful context about exhaustiveness and content (every error code, meanings, retry guidance), but it does not describe the response format or potential size. No contradiction with annotations.

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 entire description is one focused sentence with no filler. The core identity ('machine-readable catalog of every error code') comes first, followed immediately by the value-add details of meanings and retry guidance.

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 zero-parameter read-only tool, the description conveys the essential information: what the catalog contains and why an agent would use it. It does not explicitly state the output shape, but the tool is simple enough that this is only a minor 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 tool has zero parameters and an empty input schema, so there is nothing to document. Per the rubric, zero parameters receive a baseline of 4; the description does not need to add parameter-level detail.

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 resource as a machine-readable catalog of every Epsilon API error code and explicitly states the two key contents: meanings and retry guidance. No sibling tool appears to cover error codes, so there is no ambiguity about what this tool does.

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 makes the use case clear: consult this catalog when an agent needs to interpret an API error or determine retry behavior. It does not explicitly name alternatives or exclusions, but no error-focused sibling exists, and the read-only lookup context is unambiguous.

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 and destructiveHint=false, so the safety profile is covered. The description adds the useful 'No API key required' context and clarifies the return payload is full source code, but does not mention potential size, formatting, or rate-limit concerns. Reasonable value added beyond annotations.

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, information-dense sentences with zero fluff. The main purpose is front-loaded, and the auth note earns its place. There is no redundancy with the schema or annotations.

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 single-parameter read tool with full schema coverage and safety annotations, the description is nearly complete: it says what is returned, where the id comes from, and that no auth is needed. The only minor gap is that the return format (raw text vs. JSON) is not specified, but this is not critical for invoking the tool 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%, and the single 'id' parameter is well-documented in the schema with a concrete example. The description does not add parameter-level details beyond pointing to list_examples as the id source, which is the expected baseline since the schema already provides full semantics.

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 specific verb ('get'), resource ('full source code of one Epsilon integration example'), and scope ('by id from list_examples'). It clearly distinguishes itself from list_examples (which lists examples) and other sibling tools, so an agent knows exactly what it 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?

The description identifies the source of the id ('by id from list_examples') and notes that no API key is required, giving clear conditions for use. It does not explicitly name alternatives or when-not-to-use, but the 'from list_examples' pointer effectively routes the agent to obtain the correct id.

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 and destructiveHint=false, so the safety profile is covered. The description adds that this is a one-call snapshot and enumerates the returned data categories, but it does not disclose output format, pagination, or other behavioral nuances. With annotations present, this is acceptable but not rich.

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 with no filler. The key concept 'one-call market snapshot' is front-loaded, and the content breakdown follows immediately. Every phrase 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?

For a zero-parameter, read-only tool with no output schema, this description is complete enough. It tells the agent exactly what data to expect and positions it as a first-call market context tool. No missing information prevents correct invocation.

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 tool has zero parameters, and the input schema is empty, so the baseline is 4. The description adds context by explaining what the no-parameter call returns, which helps the agent understand why no arguments are needed. No schema compensation is required.

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 returns a market snapshot for Epsilon DEX with specific content: top tokens by 30-day volume, 24h volume aggregates, and engine-wide order/fill stats. This is specific enough to understand the resource and scope, though it does not explicitly contrast with siblings like market_stats or token_volume.

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?

'Good first call for market context' gives a clear usage context and implies this is the starting point for market-level queries. It stops short of explicitly saying when not to use it or naming alternatives, so it lacks full routing 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds behavioral context beyond annotations: it scopes to open/pending/active orders, includes both sides of the pair, and specifies largest-first ordering. This is useful supplementary behavior that annotations do not convey.

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 one concise sentence with no filler. It front-loads the core behavior, includes ordering information, and every phrase contributes meaning. There is no redundancy with the schema or annotations.

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 simple two-parameter read-only tool and no output schema, the description provides sufficient context by stating what is returned, the sides of the book, and the sort order. It does not detail pagination or exact return structure, but the description is adequate for an agent to invoke 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 description coverage is 100%, with tokenA and tokenB already documented as the first and second token addresses. The tool description adds no parameter-specific detail beyond referring to 'a token pair.' Baseline 3 is appropriate since the schema carries the parameter meaning.

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 and resource: 'Open (pending/active) limit orders on both sides of a token pair, largest first.' It clearly identifies this as an orderbook query and distinguishes it from siblings like get_order_status or list_orders by specifying sides, pair, and ordering.

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: an agent would call this when it needs the current open limit orders for a token pair. There is no explicit when-to-use guidance or mention of alternatives such as get_quote, get_route, or list_orders, so the context is only implied rather than stated.

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 and destructiveHint=false, so the safety profile is covered. The description adds that this is a lookup operation and specifies the returned data categories, but does not disclose much beyond that. This is adequate but not rich with extra behavioral context.

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, tightly structured sentence that front-loads the action and immediately lists the useful status enum and return contents. Every element earns its place, with no filler.

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 single-parameter read-only lookup with no output schema, the description covers how to call the tool and what to expect back. The only minor gap is not describing behavior for unknown or invalid order hashes, which is not critical given the clarity provided.

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%: the orderHash parameter is already fully documented as an EIP-712 order hash (0x-hex, 32 bytes). The description's 'by hash' phrase adds no meaning beyond the schema, so the baseline score 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 description is specific and informative: 'Look up an Epsilon order by hash' names the verb, resource, and key identifier, then lists what the tool returns (status, parameters, fills). This clearly distinguishes it from sibling tools like list_orders or get_orderbook.

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 a clear context for use: when the agent has an order hash and needs status, parameters, or fills. It does not explicitly name alternatives or exclusions, but the hash-based lookup scope makes the intended usage evident.

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 mark the tool as readOnly and non-destructive; the description adds value by explicitly stating 'only quotes; it never executes' and by flagging RAW token units as a critical behavioral detail. This goes beyond the structured metadata without contradicting it.

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 tight sentences with no filler. The main purpose is front-loaded, the critical RAW-units caveat is prominent, and the non-execution caveat closes the description efficiently.

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 read-only quote tool with three fully documented required parameters, the description is largely complete: it gives venue, direction, amount units, and non-execution behavior. There is no output schema, so a bit more detail on the quote response shape or possible failure modes would strengthen it, but it remains sufficient for correct invocation.

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?

Input schema coverage is 100%, and the schema already describes all three parameters adequately, including the RAW-unit requirement. The description reinforces the tokenIn → tokenOut direction and the decimals scaling caveat, but does not add substantial new parameter-level meaning 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 states a specific verb ('quoting'), a clear resource (swap of tokenIn → tokenOut), the venue (Epsilon on Robinhood Chain, id 4663), and explicitly notes it never executes. This clearly separates it from execution-focused siblings and leaves no ambiguity about what the tool does.

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 makes clear this is for obtaining a quote before execution and explicitly rules out execution, but it does not name alternatives like get_route or order_preflight or explain when an agent should prefer those instead. The usage context is implied rather than explicitly compared with siblings.

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, and the description reinforces this with 'Read-only.' It adds value by warning that amounts are RAW token units and clarifying that feeLegs are what a signed order embeds. There is no contradiction with annotations.

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 three short sentences with no fluff. The primary purpose and outputs are front-loaded, the read-only nature is stated separately, and the RAW units caveat is its own sentence. Every phrase 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?

With no output schema, the description compensates by naming the returned fields: venue split, expected/minimum output, price impact, and feeLegs. It captures the essence of the tool for correct invocation, though it does not enumerate every conditional interaction among orderType, triggered, and wallet.

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 parameters thoroughly. The description adds global context about RAW units and the purpose of feeLegs, but does not materially expand on individual parameter semantics beyond what the schema provides.

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 a routing breakdown for a swap, listing concrete outputs (best venue split, expected/minimum output, price impact, feeLegs). This distinguishes it from related query tools like get_quote by emphasizing the full routing and order-embedding details, not just a quote.

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?

It establishes a clear use case: when you need routing details for a swap and the feeLegs that a signed order must embed. It does not explicitly name alternatives or exclusions, so it stops short of a 5, but the purpose is concrete enough for an agent to select it over siblings like get_quote or get_orderbook.

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 and destructiveHint=false, and the description adds useful context beyond those: it is a non-authenticated operation ('No API key required'). It does not describe the return shape, but for a simple listing tool the key safety and access behaviors are covered.

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 short sentences deliver the purpose, scope, sibling routing, and auth requirement with no wasted words. The main action is front-loaded and every clause 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?

For a zero-parameter, read-only listing tool with an explicitly named sibling for source retrieval, the description is complete. The agent has enough information to decide when to call it and what to expect at a high level.

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 tool has zero parameters and schema coverage is 100%, so there is no parameter burden for the description to carry. The baseline for zero-parameter tools is 4, and the description appropriately avoids inventing unnecessary parameter details.

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 a specific action ('List') and a specific resource ('runnable Epsilon integration examples'), and it enumerates the exact kinds of examples included. It also explicitly directs the agent to get_example for the full source, which differentiates this tool from its closest sibling.

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 is explicit that this tool is for listing examples, and it names the alternative tool (get_example) to use when fetching full source. It also notes that no API key is required, giving the agent a clear prerequisite signal.

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 readOnlyHint and destructiveHint annotations already establish that this is a safe read operation, so the description only needs to add context. It adds the 'newest first' ordering behavior and the portfolio-view framing, but does not disclose pagination behavior or default return scope beyond what the schema's limit parameter already says.

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 that front-loads the action and resource, states the filtering axes, and adds ordering in four words. No filler or repetition of the title/schema.

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 an optional-parameter read-only listing tool with full schema coverage, the description plus annotations are sufficient to select and invoke it correctly. It covers scope, filters, ordering, and safety profile; no critical selection or invocation information 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 description coverage is 100%, so the input schema already documents all four parameters. The description reinforces wallet/status/type as filters and omits limit, but adds no semantics beyond the schema; 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 specifies a concrete verb ('List'), a distinct resource ('Epsilon orders'), and a clear portfolio scope with filtering dimensions (maker wallet, status, type) and ordering (newest first). This makes it easy to distinguish from singular/status-focused sibling tools like get_order_status or get_orderbook.

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 'the portfolio view' gives clear context for when this listing tool fits, and the filter dimensions suggest it is for broad order searches rather than single-order lookup. However, it does not explicitly name alternatives or state when not to use it, so it stops short of a 5.

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 and destructiveHint=false, so the read-only nature is covered. The description adds the scope and output categories, but does not disclose response shape, record counts, freshness, or pagination behavior; with no output schema, this is a moderate gap.

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 a colon-separated list of output categories conveys the tool's purpose and scope without filler. Every word contributes useful information.

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 no-parameter read-only tool, the description is mostly sufficient, but it does not define how 'Epsilon' relates to the sibling scope or explain the exact output schema beyond high-level categories. Given no output schema and several overlapping siblings, a bit more detail about what is and is not included would make it 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 are zero parameters, so no parameter documentation is needed; the schema coverage is complete at 100%. The description does not need to add parameter semantics and correctly avoids inventing any.

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 identifies the resource ('Engine-wide Epsilon stats') and specifies the exact contents: order counts by status, fill counts, and volume aggregates. It is more informative than a bare label, though it lacks an explicit verb and does not directly contrast with similarly named siblings like get_market_overview.

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 qualifier 'Engine-wide' implies this is for aggregate, cross-market statistics rather than per-order or per-token queries, but no explicit when-to-use or alternative routing is given. With many sibling tools, the absence of a direct comparison leaves some selection 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?

Annotations already mark read-only and non-destructive; the description adds that it checks oracle support/liquidity/minimum size and that amounts are raw units. This gives the agent a clear behavioral model beyond readOnlyHint. No return format is disclosed, but 'would be executable' implies a verdict.

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?

Three short sentences, front-loaded with the verb and scope, then usage timing and units. No wasted words.

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 a simple read-only preflight check, the description covers purpose, timing, checked criteria, and unit convention. The absence of an output schema is mitigated by the 'whether... would be executable' phrasing, though naming sibling tools could have further improved routing.

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 documents all three parameters at 100% coverage, so the description isn't required to compensate. It reinforces that amounts are RAW units, but no meaningful parameter semantics are added 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?

States a specific action ('Check whether'), a specific resource ('a limit/DCA order for this pair and size'), and the feasibility criteria (oracle support, liquidity, minimum size). This makes it immediately distinct from quote/route lookup siblings even without naming them.

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?

'Run this before signing an order' gives explicit when-to-use timing. It doesn't explicitly state when not to use it or name alternatives, but the pre-position relative to signing is clear 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?

The readOnlyHint and destructiveHint annotations already establish that this is a safe read operation. The description adds a valuable non-obvious behavioral detail: amounts are in RAW token units. It does not cover pagination or ordering, but the annotations lower the bar and the raw-units note is meaningful.

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 tightly written sentences with the core purpose front-loaded and no filler. The raw-units note is the only extra detail, and it earns its place as important behavioral information.

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 tool with two optional parameters and full schema coverage, the description covers the resource, the optional wallet filter, and a key output format detail. Absence of an output schema makes the return shape slightly underspecified, but the definition is still adequate for correct invocation.

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 both parameters. The phrase 'optionally filtered to one wallet' restates the wallet parameter's schema description but adds no new information about formats, defaults, or edge cases.

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 resource ('most recent swaps executed through Epsilon') and the optional scope ('filtered to one wallet'). It is specific enough to convey what the tool does, though it does not explicitly name a sibling tool to differentiate from.

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 clear context for when the tool is relevant — recent swaps, optionally for one wallet — but provides no explicit guidance about when to use it instead of sibling tools such as list_orders, get_quote, or token_volume. Usage must be inferred rather than instructed.

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 signal readOnly/destructive, and the description adds the useful auth fact 'No API key required' plus the documentation scope. It does not cover rate limits or result format details, but for a non-destructive search tool the annotations lower the burden.

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 states the action, resource, scope, result, and auth requirement with no filler. It is front-loaded and every clause is informative.

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 search tool this is complete enough: an agent knows what to search, what it will get back, and that no auth is needed. A return-format example or result schema would push it to 5, but none is required by the tool's simplicity.

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%: the query parameter has an example and the limit parameter documents default/cap. The description adds no further parameter-level detail, 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 description opens with a specific verb and resource: 'Search the Epsilon developer documentation' and lists the covered topic areas. It also states the return behavior ('Returns the most relevant doc sections'), which clearly separates it from the data/order sibling tools.

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 makes the tool's context clear: it is for looking up Epsilon API/auth/signing/webhook documentation rather than for market data or order operations. It does not explicitly name alternative tools or exclusion criteria, so it stops short of 5.

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 and destructiveHint=false, so no contradiction exists. The description adds useful behavioral context: it returns address and decimals, supports address lookup as well as symbol/name fragments, and clarifies how to disambiguate results using volume30dUsd. It does not describe the full response structure, but the annotations cover the safety profile.

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 tight sentences with no filler. The primary purpose is front-loaded, the usage directive follows immediately, and the disambiguation tip earns its place by addressing a real practical issue.

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 low-complexity 2-parameter tool with read-only annotations, the description is largely complete: it explains the core function, the call-first workflow, and the disambiguation cue. There is no output schema, so a bit more return-shape detail could help, but the essentials for correct invocation are present.

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 parameters are already fully documented in the input schema. The description adds tool-level context around the lookup concept and the volume30dUsd output field, but it does not significantly expand on the input parameters themselves. The baseline of 3 applies because the schema carries the parameter documentation burden.

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 ('Resolve a token symbol or name to its address and decimals') and distinguishes the tool from all siblings by noting that every other tool takes addresses. It also mentions the disambiguating volume30dUsd field, making the tool's role unambiguous.

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 when-to-use guidance: 'call this FIRST when the user names a token; every other tool takes addresses.' It also explains how to handle same-symbol ambiguity by checking volume30dUsd, which is concrete and actionable.

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 and destructiveHint=false, so the safety profile is covered. The description adds useful context about the granularity (per-token and total) and the fact that it reports swap volume, but it does not disclose additional behavioral details such as result structure, ordering, pagination, or any rate-limit/auth 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 a single compact sentence that front-loads the core purpose and enumerates the window options in parentheses. There is no redundant text, no filler, and it is immediately scannable by an agent.

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 metric tool with one optional parameter and no output schema, the description gives enough context to select and call it: it states the output type (swap volume), the aggregation granularity (per-token and total), and the available windows. A more detailed explanation of return values or default behavior would improve completeness, but the description is largely sufficient given the tool's low 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?

The schema already provides a full description of the single 'window' parameter, including its allowed values and default. The tool description essentially repeats this same information without adding any new semantic meaning, so it adds no value beyond the schema and merits the baseline score.

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: reporting per-token and total swap volume over a selectable time window. It communicates the resource (swap volume) and the main variants (1h, 24h, 7d, 30d, all), but it does not explicitly differentiate itself from sibling tools such as recent_swaps or market_stats, and it lacks an explicit verb like 'get' or 'fetch'.

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: whenever per-token or total swap volume for a given window is needed. However, it provides no explicit guidance about when not to use it or which alternative sibling tool should be preferred for related but different data, leaving some ambiguity for tool selection.

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