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

With no annotations, the description carries the full burden of behavioral disclosure. It correctly implies a financial transaction, but it does not state that executing spends SOL from the wallet, that the trade is irreversible, or that slippage may affect the final price. The 'execute or quote' dual mode is mentioned but not explained behaviorally.

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 front-loads the action, target token, venue, and wallet context. There is no filler or redundant restatement of the tool name.

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 financial transaction tool with no annotations and no output schema, the description omits critical operational details: how the agent selects execute vs quote, what the return value looks like, whether the wallet must be funded, and what failure/slippage behavior to expect. This is not complete enough for an agent to invoke it with full confidence.

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 amountSol and slippagePercent well. The description adds no additional parameter-level meaning and does not clarify how the 'quote' vs 'execute' mode maps to the parameters, but the baseline 3 is appropriate because the schema handles parameter documentation.

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 ('execute or quote'), a specific resource ('$TPST buy order'), and the venue ('Pump.fun'). The tool is clearly distinguished from sibling tools like colosseum_status or colosseum_leaderboard, which have different purposes.

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 the agent needs to buy $TPST, but it gives no explicit when-to-use or when-not-to-use guidance, and it does not mention any alternative tool. There is also no explanation of when 'execute' should be chosen over 'quote', even though the description presents both modes.

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 the behavioral burden. 'Discover' implies a read-only listing, and the listed fields hint at the return content, but it does not disclose potential pagination, ordering, staleness, or whether the result set has any limits.

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 tight, front-loaded sentence that states the tool's function and the follow-up action. Every clause earns its place and there is 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?

For a parameterless tool, the description covers the essential purpose, the result fields, and the next-step integration with colosseum_fight. It lacks explicit detail about return format or size limits, but the core call is fully understandable.

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, so the schema provides nothing to clarify. The description adds meaning by specifying what information each returned agent includes, which is enough for a parameterless directory tool.

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 clear action ('Discover') and a specific resource ('registered external agents') and enumerates the returned fields (agentRef, level, Elo, record). It also explicitly connects the tool to colosseum_fight, distinguishing its purpose from that 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 explains how to proceed after discovery: fight an agent via colosseum_fight with opponentId set to its agentRef. This is clear practical guidance, though it does not explicitly contrast this tool with other sibling tools such as colosseum_leaderboard.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It does disclose a side effect (15 energy cost), the battle length (3 rounds), and the tactical resolution rules (rock-paper-scissors), which are meaningful. However, it does not state what happens on win/loss, energy deduction timing, or any failure/cooldown conditions, leaving gaps for an agent to discover.

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, each carrying distinct information: purpose, cost, and rules. There is no fluff or repetition of the schema, and the purpose is front-loaded. It is appropriately concise.

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 2-parameter tool with no annotations and no output schema, the description covers the main action, cost, and tactical mechanics, which is adequate for basic invocation. However, it does not explain what the tool returns (battle result, rewards), how to obtain a valid opponentId (only the schema hints at it), or behavior on invalid input/insufficient energy, so an agent is left with some uncertainty.

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 fully documents both parameters (opponentId and tactics) with descriptions, so the baseline is 3. The description adds value by explaining how the tactics parameter behaves: the counter relationships (Aggressive beats Balanced, etc.), which are not inferable from the schema alone. This raises it to a 4.

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 action ('Execute a 3-round battle') and target ('against an opponent'), which is specific and not a tautology. However, it does not explicitly contrast with sibling tools such as colosseum_spar or colosseum_match, so an agent must infer the differentiator from the name and context.

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

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

The description provides no guidance on when to choose this tool over colosseum_spar or colosseum_match, nor any exclusions or prerequisites beyond energy cost. The only hint about sourcing opponentId appears in the schema, not the tool description, so the description itself lacks usage routing.

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 the full burden. 'Query' clearly signals a read-only operation remainder, and the global/Elo scoping is useful, but it does not address response format, list limits, or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence states the action and scope with no filler. It is immediately scannable and every word adds value.

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 query, the description is nearly sufficient: an agent knows what to call and what ordering to expect. It is slightly limited by not describing the returned ranking payload, but the absence of parameters and output schema lowers what is required.

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 properties schema, so there are no parameter semantics for the description to clarify. The baseline for a no-parameter tool is 4, and the description adds no misleading or missing parameter information.

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 concrete verb, 'Query', names the specific resource, 'global Colosseum leaderboard rankings', and clarifies ordering by Elo. This clearly differentiates it from siblings like colosseum_status, colosseum_match, or colosseum_buy_token.

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 no guidance on when to use the leaderboard tool versus sibling tools, and it mentions no exclusions or alternative conditions. An agent must infer usage solely from the sibling 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the visible outcome (finding an opponent and revealing their stance) but does not disclose whether this operation has side effects on the queue, costs anything, requires state, or blocks waiting. The description is not misleading, but it is incomplete for a tool with no annotation 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?

A single sentence communicates the action, the domain, the matching criterion, and the expected result with no filler. Every phrase adds meaning, and the core behavior is 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?

For a zero-parameter tool this is reasonably complete, but the absence of an output schema means the description should clarify what the caller receives and what happens when no opponent is found. It also does not explain how matchmaking placement interacts with the queue state or sibling tools, leaving some practical ambiguity.

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 zero parameters and a 100% schema description coverage ratio, the schema is inherently complete and the description does not need to explain parameter behavior. The baseline for a zero-parameter tool is 4, and the description adds no conflicting or confusing parameter information.

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 ('Find') and a specific resource ('nearby Elo-matched opponent in the Colosseum matchmaking queue'), and it adds the concrete outcome of revealing the opponent's tactical stance. This clearly distinguishes the tool's core action from the 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 implies a clear use case: use this when you want to locate a matchmaking opponent. However, it does not explicitly state when to prefer this over siblings like colosseum_spar or colosseum_fight, nor does it mention any exclusions or preconditions.

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 present, so the description carries the burden. It discloses the two key behavioral consequences—no energy penalty and no Elo loss—making the operation safe and low-stakes. It does not describe output or termination, but for a zero-parameter spar command, the disclosed effects cover the main risk.

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 with no filler; the key facts are front-loaded in the first sentence. Every clause adds selection-relevant 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?

Given zero parameters and no output schema, the description covers who, what, cost, and best use. It stops short of saying what the caller receives after the challenge, but this is minor for a no-argument command.

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 no parameters, so the baseline is 4. The description does not need to add parameter meaning, and there is no schema-coverage gap to compensate.

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?

Identifies the exact action ('Challenge Muse') and the resource ('persistent house sparring bot'), which clearly separates it from competitive match/fight siblings. The phrase 'sparring bot' conveys it is a practice opponent.

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?

States an explicit use case: testing tactics with zero costs and zero risk. It does not name alternatives or when-not conditions, but the practice-vs-competition contrast with sibling names is implicit.

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 the behavioral disclosure burden. It signals a non-destructive read operation via 'Inspect,' and the field list sets expectations for what is returned. However, it does not disclose any behavior beyond the obvious status read, such as whether the wallet is externally controlled or whether data is cached/refreshed.

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, efficient sentence that leads with the action and immediately specifies the resource and relevant fields. There is no filler, repetition, or unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless status-inspection tool, the description fully covers what the agent needs to know: the resource and the specific state fields returned. The absence of an output schema is mitigated by the explicit field list, and the sibling tool names further disambiguate its role.

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 schema documents this fully with 100% coverage. There is no parameter ambiguity for the description to resolve, so the baseline for a no-parameter tool 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 uses the specific verb 'Inspect' and clearly names the resource: 'gladiator agent state.' It enumerates the exact fields (level, energy, Elo, wins, losses, win streak, wallet), making its purpose unmistakable and clearly distinct from siblings like colosseum_fight or colosseum_match.

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

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

There is no explicit guidance on when to use this tool versus alternatives such as colosseum_leaderboard or colosseum_spar. The verb 'Inspect' and the read-only nature of the state make the usage context reasonably implied, but no exclusions or alternative-selection rules are 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?

With no annotations, the description carries the behavioral burden. It signals a non-mutating query, real-time freshness, and the data source (Pump.fun/Solana), which is useful. It does not disclose rate limits, staleness bounds, or response shape, but for a zero-parameter read-only fetch the burden is modest.

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 packs the key identifiers: token ($TPST), source (Pump.fun), chain (Solana), and the returned metrics (bonding curve, price in two currencies, market cap, DEX info). 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 zero-parameter read-only tool with no output schema, the description covers what data the agent will receive and where it comes from, so invocation is unambiguous. It could be slightly more complete by stating the exact output format, but the listed metrics are the main contract.

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 no parameters and 100% schema coverage, so the baseline is 4. The description names all returned data categories and therefore does not need to explain input 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?

The description uses a specific verb ('Query') and names the exact resource: $TPST Pump.fun bonding curve metrics, price in USD/SOL, market cap, and DEX info on Solana. This clearly distinguishes token_info from siblings like buy_token, status, and match.

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 is clear this should be used when an agent needs current $TPST valuation and bonding-curve/DEX context on Solana. It does not name excluded cases, but it does not need to: the tool is a fixed-token query with zero parameters, and sibling tools cover other actions.

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