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

Goes well beyond annotations by disclosing rate limits (10 launches per wallet per day), the 15% dev buy cap, the 5 second sniper window, fee/mode economics, and the server-side vanity mint behavior when customMint is absent. These are meaningful behavioral constraints that annotations do not carry. It stops short of explaining transaction expiry, error conditions, or exactly what the unsigned transaction contains.

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?

Front-loads purpose and core constraints in three dense sentences with little waste. The long parenthetical rule list is slightly run-on but every clause carries information about fees, caps, or signing behavior.

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 12-parameter mutation-style build tool with no output schema, the description covers the essential semantics, signing requirement, rate limits, and server behavior. It would be more complete if it stated the shape of the returned unsigned transaction and any failure or expiry behavior, but the core call-preparation context is 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?

With only 50% schema description coverage across 12 parameters, the description compensates well for the most consequential ones: mode is explained in terms of creator/holder earnings, customMint triggers server-side mint selection and an extra signature, and devBuySol is bounded by the 15% supply cap. Several metadata parameters (xUrl, website, telegramUrl, description, name/ticker) receive no explanation beyond the schema, which keeps it from a 5.

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 and resource: 'Build the create transaction for a new coin on justi.fun,' and immediately distinguishes it from a send operation with 'nothing is sent.' An agent can tell this is the launch-preparation step rather than a swap or query without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it by saying the creator wallet must sign the result and nothing is sent, but it never names an alternative sibling or an explicit when-not condition. The signing requirement is a prerequisite, not a usage guideline, so the agent must infer the workflow.

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?

Goes well beyond the annotations: nothing is signed or sent, the user's wallet must sign, the server re-quotes, simulates, and sets compute limit and priority fee. That explains the non-destructive but state-changing workflow clearly. It stops short of stating auth requirements or whether the quote can expire.

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?

Four sentences, front-loaded with purpose, then the no-signing constraint, then server behavior, then the return shape. No filler and every sentence carries 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?

With no output schema, spelling out the return (swapId, base64 tx, quote, submission instructions) is genuinely useful, and the simulation/priority-fee behavior is covered. The gaps are the amount-parameter selection rules and slippage defaults for an 8-parameter 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 coverage is 63%, so the schema already documents most fields, including the buy/sell amount fields. The description only mentions priority fee indirectly and adds no guidance on which amount parameter to use per side or on slippage defaults, so it doesn't compensate for the uncovered 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?

States a specific verb and resource ('Build an unsigned Solana v0 transaction that buys or sells a justi.fun coin') and its scope (unsigned, per-wallet). The 'unsigned build' framing clearly separates it from justi_quote and from the signing/submission siblings like justi_tx_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: you call this to get a swap transaction to sign. It never explicitly says when to prefer justi_quote first, or when not to use this (e.g. for launches, which belong to justi_build_launch). No alternatives or exclusions are named.

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 and openWorldHint, so safety is covered; the description's added value is enumerating exactly what comes back (socials, fee split, safety facts, bonding curve progress, graduation/DAMM v2 pool, sniper window, totals). With no output schema, that return-shape disclosure is genuinely useful. It stops short of noting not-found behavior or data freshness for an open-world live 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?

One front-loaded sentence with the key (mint) stated early and no filler. The trailing field list is dense but each item signals real payload content an agent may need to plan around.

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 one-parameter read with no output schema, the description covers the important ground by describing the returned record's composition. Remaining gaps (behavior for invalid/nonexistent mints, whether the payload is live or cached) are minor for a read-only lookup.

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% and the single parameter already carries a base58 pattern and "Coin mint address" description. The description only restates "by mint", adding no format hints, case sensitivity, or examples, 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?

Names a specific retrieval ("Full detail of one coin") plus the lookup key (mint), and the phrase "one coin" implicitly contrasts with the sibling justi_list_coins. It does not name justi_list_coins explicitly, so differentiation is inferred rather than stated.

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 the per-coin lookup to run once it has a mint (e.g., from justi_list_coins or a trade). There is no explicit when-to-use/when-not guidance, no mention of what to do if the mint is unknown, and no alternatives named.

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 and openWorldHint, so the safety profile is covered; the description adds genuine context by disclosing the default ordering and the return shape ('compact rows and nextCursor'), which matters because there is no output schema. It doesn't mention rate limits or what fields 'compact rows' actually contain.

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 sentences, zero waste, with the resource identification and default ordering front-loaded before the parameter guidance and return note.

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 does the necessary work of noting compact rows plus nextCursor for paging, and the filter surface is covered by the schema. Minor gaps: no guidance on the boundary with justi_get_coin and no sense of what a 'compact row' includes.

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 already 83%, with enum values and the status semantics documented in the schema itself. The description largely restates the sort enum and the q behavior already described in the schema, adding little beyond 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?

Specific verb+resource ('List coins launched on justi.fun') with the platform identified as a Solana launchpad on Meteora, plus the default ordering stated. The dual list/search framing plus 'pass an exact mint' implicitly separates it from the single-coin sibling justi_get_coin.

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?

Explains how to search (q for ticker/name, exact mint, or filter by sort) and that newest-first is the default, giving clear usage context. It stops short of exclusions, e.g. it never says to use justi_get_coin instead when you already have a mint and want full detail.

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 openWorldHint=true, so safety and external-data exposure are covered. The description adds the metric categories being totaled, which is meaningful value, but says nothing about data freshness, whether totals are cumulative historical or a current snapshot, or how recently they are computed — a real concern for an open-world stats 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?

One sentence, front-loaded with the scope ('Platform-wide totals of justi.fun') followed by the metric list. It is efficient with no filler, though the phrase overlaps substantially with the title rather than adding new framing.

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 carries the burden of telling the agent what comes back; the metric list partially does this, but leaves open units, snapshot vs. cumulative semantics, and whether data is live or cached. Given the tool is simple and read-only, this is adequate but leaves a genuine gap for an open-world stats call.

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 takes zero parameters, so there is nothing to disambiguate; baseline 4 applies. The description avoids inventing or misdescribing inputs.

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-free but precise resource: platform-wide aggregate totals, and enumerates the metrics (coins launched, volume, fees, holder payouts, burns). This clearly distinguishes it from per-coin siblings like justi_get_coin, justi_recent_trades and justi_tx_status, which are all scoped to individual items rather than platform aggregates.

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 the tool for 'give me overall platform numbers' as opposed to per-coin or per-transaction lookups. There is no explicit when-to-use / when-not-to-use statement and no naming of an alternative (e.g. justi_protocol_info), which is the obvious potential overlap.

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 openWorldHint=true, so the safety profile is covered. The description adds that this is a static knowledge/policy surface rather than a live query, but says nothing about return shape, size, or caching 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?

Front-loaded with the core purpose, then a compact comma-delimited topic inventory. The list is dense and slightly comma-spliced, but every item is a genuine content pointer rather than 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 zero-parameter reference tool with no output schema, the description must convey what comes back, and it does so by enumerating the covered topics. An agent knows exactly what questions this tool can answer before calling 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?

Zero parameters, so there is nothing to disambiguate; baseline 4 applies. The description correctly signals that no arguments select a sub-topic, implying the whole reference is returned at once.

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+resource: what justi.fun is and how it works on chain, then enumerates the exact content domains (Meteora DBC program, fee tiers, sniper window, dev buy cap, graduation). This lets an agent distinguish it immediately from action-oriented siblings like justi_build_launch or justi_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?

"Use this before explaining fees or building a launch" gives a concrete trigger condition tied to two downstream tasks. It does not explicitly name an alternative tool to use instead when this one is wrong, so it falls 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?

The annotations already establish readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds meaningful behavioral context: pricing depends on whether the coin is pre- or post-graduation, and the response includes expected/minimum output, price impact, fee amount, and fee recipients.

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: the first establishes purpose and venue behavior, the second covers side-specific inputs and return values. It is front-loaded and contains 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 read-only quote tool with no output schema, the description explains the relevant return fields and platform-dependent pricing behavior. The main remaining gap is an explicit statement that this does not execute a trade, though readOnlyHint=true already signals that.

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 side-dependent meaning beyond the schema by tying amountSol to buys and amountTokens/amountRaw to sells, including that amountTokens is in whole tokens. SlippageBps is left to the schema, which already documents its default and range, so the 67% schema coverage is reasonably supplemented.

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: "Quote a trade on a justi.fun coin," and clarifies the pricing venue changes from bonding curve to Meteora DAMM v2 after graduation. It is clearly a quoting tool rather than an execution tool, though it does not explicitly name justi_build_swap as the execution 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?

It gives concrete input guidance: use amountSol for buys and amountTokens or amountRaw for sells, with whole-token semantics for amountTokens. However, it does not explicitly state when to use this instead of justi_build_swap or that it only previews a trade and does not execute 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 and openWorldHint, and the description adds real value on top: newest-first ordering, coverage of both pre- and post-graduation venues, and unit disclosure (amounts in SOL and whole tokens) that an agent would otherwise have to guess. It is silent on pagination behavior and result-size caps, which keeps it below a 5.

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, no filler, with the core identity and ordering front-loaded and filtering/units following. Every clause conveys information an agent needs.

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 five parameters, low schema coverage, and no output schema, the description should describe the shape of returned trades (price, timestamp, tx signature, side) and how cursor/limit interact. It covers venue scope and units well but leaves the return shape and pagination mechanics unspecified.

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 only 20% (just limit), so the description carries most of the burden; it does explain that side and wallet act as filters, which gives those two params meaning beyond their bare types and enum. The mint parameter and, critically, the cursor parameter receive no explanation in either the schema or the description, leaving the pagination contract undefined.

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 concrete resource (trades of one justi.fun coin), the ordering (newest first), and the venue scope (bonding curve plus DAMM v2 after graduation), which is far more specific than the title alone. It doesn't name a sibling to differentiate from, but no sibling tool in the list covers trade history, so the risk of mis-selection is low.

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?

"Filter by side or wallet" implies the two narrowing options, giving some usage context. However, there is no explicit when-to-use guidance, no mention of pagination workflow despite a cursor parameter, and no statement of what happens when filters are omitted.

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 and openWorldHint, so the safety profile is covered; the description adds real value beyond that by disclosing the possible status values and the fact that results are enriched with the originating swap/launch. It stops short of saying what happens for an unknown or non-justi signature (error vs. bare status), which is the one remaining behavioral question.

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 front-loaded sentence with no filler; the status enumeration and the justi.fun scoping caveat each earn their 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 one-parameter read tool with no output schema, the description covers what is returned (status values plus associated swap/launch) and the input scope. Only the edge-case behavior for unrecognized signatures is left unstated.

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 0%, but the JSON schema's base58 pattern already constrains the format; the description contributes the important semantic point that the parameter accepts ANY Solana signature, not only justi.fun-built ones, which prevents an agent from wrongly narrowing its use. It does not add format or example details, but the pattern covers that.

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 resource – the status of any Solana signature – and enumerates the full result space (pending, confirmed, finalized, failed, unknown) plus the enrichment (associated swap or launch). No sibling tool does anything comparable, so an agent can distinguish it from justi_recent_trades or justi_quote without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the phrase 'when it was built through justi.fun' signals this is the follow-up check after justi_build_swap or justi_build_launch, but the description never says when to call it or what to do instead for non-justi transactions. No prerequisites or exclusions are given.

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