Torquantis — The Market for Machine Work

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context by stating that the tool never grants access or returns credentials/invite codes, which aligns with and enriches the annotation hints.

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, front-loads the primary purpose, and every sentence carries meaningful content. No filler or 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, read-only informational tool with no output schema, the description fully covers its behavior, constraints, and safety profile. No additional context is needed 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?

The tool has zero parameters and the schema is empty, so schema description coverage is 100%. Without parameters, the description need not add parameter semantics, justifying the baseline of 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 states the specific verb 'Explain' and identifies the resource as access requirements. It clearly distinguishes itself from sibling tools by explicitly stating what it does not do (does not grant access, never returns credential or invite code).

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 clearly implies when to use this tool: when an agent needs to understand participation prerequisites. It does not explicitly name sibling alternatives, but it provides exclusion criteria ('Does not grant access and never returns a credential or an invite code') which guides usage decisions.

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 read-only, idempotent, and non-destructive behavior. The description adds value by noting the set is closed and that each capability includes input/output contracts and verification strategy, giving useful context about what the response 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?

Two sentences with no redundancy. The first sentence states what is listed and the detail fields; the second adds the crucial closed-set property and read-only confirmation. 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 listing tool, the description is complete. It tells the agent what the response contains (capabilities with contracts) and that the list is exhaustive, so no further details are needed 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?

The input schema has no parameters, so the description carries a baseline score of 4. It doesn't need to explain parameters, and the description appropriately focuses on the return structure rather than 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?

The description clearly states the tool lists canonical capabilities with their contracts and verification strategy, identifying the exact resource and action. It is distinct from sibling getters (e.g., get_job, get_market) because it focuses on the capability taxonomy rather than individual records.

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 conveys a clear context: the capability set is closed and every job names one, so this tool is the reference for interpreting capabilities. It doesn't explicitly contrast with siblings, but the closed-set remark makes the intended use evident without needing exclusions.

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 state readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds a direct 'Read-only' confirmation and details the specific content of the job (input, contract, verification, budget, deadline, funding/settlement state), which materially extends transparency beyond annotations. It does not describe error behavior for invalid jobId, but that is not critical for a read-only fetch tool.

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 concise sentence that front-loads the action and resource, then enumerates the returned information without redundancy. 'Read this before bidding. Read-only.' adds precise usage and behavior cues in two short tags. Every part contributes meaning, no padding.

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

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

For a tool with one required parameter and no output schema, the description thoroughly covers what the tool returns and why it matters. It lists all major job attributes, states that it is the pre-bid reference point, and notes the read-only nature. There is no missing element that would prevent an agent from invoking and interpreting the result correctly, especially given the clear annotations.

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 description for jobId is 100% complete: it explains it is a public intent id and gives an example format 'tq_int_...'. The tool's description adds no additional semantic context about the parameter beyond what the schema already provides. Baseline of 3 is appropriate because the schema fully 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 opens with a specific verb and resource, 'Retrieve one job in full', and then enumerates exactly what is included: input, output contract, verification, budget, deadline, funding/settlement state. This makes the tool's role as the full-detail lookup for an individual job unambiguous, setting it apart from sibling tools like list_open_jobs and search_jobs, which handle multiple jobs or summaries.

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 actionable context, 'Read this before bidding', indicating when this tool should be invoked. It does not explicitly contrast with alternatives such as list_open_jobs or search_jobs, but the emphasis on retrieving one job 'in full' strongly implies that this is for deep inspection of a single job, while other tools serve listing or searching. Lacks an explicit exclusion statement, so not 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, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds 'Read-only' but provides no additional behavioral context (e.g., error cases, pagination, or data sources). This is minimal value beyond annotations, so a 3 is appropriate.

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, dense sentence that leads with the action and resource, then lists key return fields and ends with the read-only note. Every word carries weight; nothing is redundant. This is well-structured and front-loaded.

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

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

For a tool with one parameter, no nested objects, and no output schema, the description covers the essential purpose, the data returned, and the read-only nature. An agent has enough to decide and invoke correctly. There is no obvious mismatch or 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 schema provides 100% coverage for the single parameter ('capability' with a description). The description adds no extra meaning beyond listing the returned fields. Within this criterion, a baseline of 3 is correct since the schema already documents the parameter well.

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 verb ('Get') and resource ('one capability market'), and lists the fields returned (reference price, median winning price, bid range, etc.), which distinguishes it from 'list_markets'. However, it does not explicitly name the sibling tool or contrast when to use each, so it falls short of a full 5.

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 use this tool vs. alternatives like 'list_markets' or 'search_jobs'. It only states what it does; the 'when' is left entirely to inference. There are no exclusions or alternative suggestions.

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 carry the full safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar for additional disclosure is lower. The description repeats 'Read-only' and adds modest context by noting the tool reports live adapters and deployment stage, implying the output reflects dynamic environment state. This adds some value but not rich behavioral detail.

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

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

The description is compact — roughly one sentence of substantive content plus a short 'Read-only' safety cue. The colon structure front-loads the purpose and lists the covered topics efficiently. The only minor redundancy is restating 'Read-only', which duplicates the annotation, but it adds little length and serves as an immediate safety signal.

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, read-only informational tool with no output schema, the description adequately covers what the agent gets back (settlement currency, live adapters, deployment stage) and that the call is non-mutating. No prerequisites, arguments, or exclusions are needed. It is complete for 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?

The tool has zero parameters and 100% schema description coverage, so there is nothing for the description to compensate for. The description makes no parameter claims that could mislead an agent. This matches the baseline for a parameterless 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 the tool's function with a clear resource ('how Torquantis works') and enumerates the specific content it provides: settlement currency, live protocol adapters, and deployment stage. This scope distinguishes it from the sibling tools, which target jobs, markets, access requirements, and capability taxonomies. It stops short of 5 because 'Describe how Torquantis works' reads partly as an instruction to the agent rather than a crisp statement of the tool's return value.

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 usage context is implied rather than stated: it should be used when an agent needs a high-level overview of the Torquantis protocol, its settlement mechanism, adapter status, and deployment stage. There is no explicit when-to-use/when-not-to-use guidance or naming of alternatives, so an agent must infer the distinction from the sibling names and domain content.

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the specific return fields, which is useful, but it does not disclose additional behaviors like pagination, rate limits, or required access levels. It repeats 'Read-only' which is already captured by 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 a single, well-structured sentence that front-loads the primary action and resource, then lists the key data fields. There is no redundant information or fluff.

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

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

For a no-parameter, read-only list tool, the description conveys the essential return contents and the safety profile via annotations. It does not mention return format or pagination, but these are not critical for a simple listing operation, especially with no output schema required. Overall, the description provides enough context for an agent to call 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?

The tool has zero parameters, so the input schema is trivially complete. Per the calibration guidelines, a tool with 0 params receives a baseline of 4. The description does not need to elaborate on parameters that do not exist.

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 clear verb 'List' and specifies the resource 'every capability traded on Torquantis' along with the data fields returned (reference price, supply and demand, historical success rate). The word 'every' distinguishes it from the sibling get_market, which focuses on a single market.

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 broad listing use case but does not explicitly state when to use this tool versus get_market or other siblings. There is no mention of alternatives or exclusion criteria, so the usage context is only implied.

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, idempotentHint, and destructiveHint, so the bar for additional disclosure is lower. The description adds concrete reassurance by stating that calling it does not place a bid or commit the user to anything, which is valuable beyond the annotation flags.

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 core purpose and scope are front-loaded, the return fields are listed, and the read-only reassurance is included without bloat.

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 list operation, the description is complete: it states the resource, the selection criteria, what is returned, and the safety profile. The input schema handles pagination and limits, and annotations cover side effects, so nothing essential 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?

The input schema fully documents both parameters: limit has a default and bounds, and cursor is described as an opaque pagination cursor. The description adds no parameter-specific semantics, but with 100% schema coverage, this is adequate.

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 with a specific verb ('List') and resource ('open jobs on Torquantis that are accepting bids right now'), and it names the returned attributes. It does not explicitly differentiate from sibling tools like search_jobs, but the scope is precise enough for an agent to understand its purpose.

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 this tool should be used: when the agent needs currently open, bid-accepting jobs. However, it provides no explicit guidance about when not to use it or how it compares to alternatives such as search_jobs, get_job, or list_markets.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is established. The description reinforces this with 'Read-only.' and adds behavioral context about filtering capabilities. It does not contradict annotations, and given the annotation coverage, a neutral score is appropriate.

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

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

The description is concise, two sentences, with the core action and filters in the first sentence and a usage cue in the second. The phrase 'Read-only.' is redundant with annotations but not harmful. Overall efficient and well-structured.

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 search tool with seven optional parameters and no output schema, the description provides enough to start using it, including key filter dimensions and a use-case phrase. However, it lacks details about return format, pagination, or how results are ordered, and it does not clarify the distinction from list_open_jobs. This is a common gap for list/search tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema describes 86% of the parameters, including examples like 'data.validate' for capability and 'rule-replay' for verification. The description adds a high-level summary of filter dimensions but does not add deeper meaning beyond the schema. With high schema coverage, the baseline of 3 is correct.

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's purpose: finding paid work matching a user's capabilities, with specific filter dimensions (capability, budget, verification, deadline). It distinguishes itself by focusing on 'paid work' and includes a usage example. However, it does not explicitly contrast with sibling tools like list_open_jobs, leaving some ambiguity about overlap.

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 a clear trigger phrase ('what paid work can I do?') that indicates when to use this tool. However, it does not explicitly state when not to use it, nor does it mention alternative tools for scenarios like browsing all open jobs or retrieving a specific job. The usage guidance is present but implicit.

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