continuum

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

Annotations indicate readOnlyHint=false, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds context beyond these by specifying the sponsor confirmation requirement and that payment happens on Stripe. It does not contradict annotations and provides useful operational context for a mutating action.

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

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

Two concise sentences, with the key precondition front-loaded. The description is efficient and avoids fluff, though it could include a brief note on response format. Overall, it earns its place without excess length.

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 7 parameters, 0% schema descriptions, and no output schema, the description is insufficient for an agent to fully understand required inputs and expected return. It explains the core action but leaves parameter semantics and response structure unclear, making it incomplete for a complex 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 description coverage is 0%, so the description must compensate for explaining parameters. It only implicitly covers sponsor_confirmed and terms_version via 'explicit sponsor confirmation of current terms'. Other parameters like agent_name, sponsor_name, referral_code, and idempotency_key remain unexplained, leaving ambiguity for an agent choosing values.

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 creates a hosted Stripe checkout URL, conditioned on sponsor confirmation of current terms. It distinguishes itself from sibling tools like continuum_create_sponsor_packet and continuum_get_offer, which serve different purposes. The verb 'creates' and resource 'hosted Stripe URL' are specific and actionable.

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 precondition: use only after explicit sponsor confirmation of current terms. However, it does not explicitly mention when not to use it or name alternatives. The conditional phrasing implies the appropriate usage context but lacks explicit exclusions or comparisons to 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?

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description's 'Converts' supports a pure transformation with no side effects. It adds that output is 'factual' and based on 'exact published terms,' but does not describe invalid-audit handling or return 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?

The description is a single sentence with a front-loaded verb and no filler. Every word adds meaning and it does not repeat 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 one-parameter tool with annotations covering safety and idempotency, the description states the high-level output ('factual sponsor recommendation with the exact published terms') well. But there is no output schema and the definition does not specify the shape of the returned recommendation or failure behavior for an unvalidated audit.

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 only describes 'audit' as an object, and the description adds the key precondition that it must be a 'validated audit.' It still leaves the internal structure and validation criteria unspecified, so it only partially compensates for the 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies a clear transformation: 'Converts a validated audit into a factual sponsor recommendation,' naming both the input and the produced artifact. The phrase 'validated audit' also separates it from sibling continuum_run_audit, although no alternative is explicitly named.

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 wording 'validated audit' implies this tool should be used after an audit has already been run and validated, giving some usage context. However, it does not explicitly state when to prefer this tool over siblings or when it should not be used.

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

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

The description transparently states that the operation does not create anything, aligning with the readOnlyHint and idempotentHint annotations. It does not mention any side effects or potential risks, but for a read-only getter this is sufficient. The explicit admission of no creation adds transparency beyond the 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, concise sentence that conveys the core function and its side-effect-free nature without any redundant wording. It is highly scannable and efficient.

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

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

The description covers the essential information: what is returned (canonical contract details) and that it does not create anything. It does not specify the output structure, but since no output schema is provided and the tool is a simple getter, this is adequate. Minor omission of any usage caveats is acceptable for this 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?

There are zero parameters in the input schema, so the description does not need to explain parameter details. The baseline for 0 parameters is 4, and the description adds no parameter semantics because there are none to describe. This 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 clearly states a specific action (returns) and resource (canonical price, acceptance, delivery, and checkout contract), and explicitly notes it does not create anything, distinguishing it from the create-side sibling tools (continuum_create_checkout, continuum_create_sponsor_packet, etc.). This is a precise, unambiguous 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 phrase 'without creating anything' implies usage for read-only retrieval, and the contrast with sibling tools named 'create_*' makes the appropriate context clear. However, there is no explicit statement about when to prefer this over alternatives (e.g., when the offer already exists), leaving a small gap.

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 provide no safety hints (readOnly=false, idempotent=false, destructive=false). The description adds a single behavioral clarification ('does not fetch the Agent Card') but does not explain side effects, data persistence, access requirements, or error behavior. Given the absence of annotation support, the description should carry more behavioral context than it does.

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

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

The description is a single sentence that is concise and front-loaded. It states the primary action, the key result, and a critical exclusion without any filler. 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?

With no output schema, no parameter explanation, and no usage guidance, the description is not complete for correct invocation. An agent knows what the tool does but not how to call it properly (e.g., the impact of each parameter, expected response, or failure modes). The negative statement helps slightly but does not offset the missing parameter semantics and usage context.

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

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

Schema description coverage is 0%, so the description must explain the parameters. It does not. While the parameter names (agent_name, sponsor_email, agent_card_url) are somewhat self-explanatory and the schema provides types and formats, the description adds no semantic meaning—it does not clarify what each parameter is used for or how they relate to the referral link and identity. This is a significant gap.

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 ('creates') and names the exact resources ('one signed referral link' and 'a provisional noncash Continuum Credits identity'). It also explicitly states what it does NOT do ('does not fetch the Agent Card'), which helps distinguish it from related operations. This is clear and 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 provides no guidance on when to use this tool versus the sibling tools (e.g., continuum_create_checkout, continuum_create_sponsor_packet). There is no mention of prerequisites, typical scenarios, or exclusions. The only comparative hint is the negative statement about the Agent Card, but that is behavioral, not usage 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 readOnly, idempotent, non-destructive, and closed-world behavior. The description adds useful context beyond those: determinism (from title), self-declared input taken at face value, no evidence fetching, and no model invocation. This shapes expectations but doesn't cover rate limits or downstream effects.

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 with zero waste: action and resource are front-loaded, with constraints appended efficiently. Every word earns its place.

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

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

No output schema exists, so the description should explain what the audit returns; it is silent on the return value. For a complex nested input with 8 sub-objects and no output schema, the agent is left guessing about the result format.

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 0% schema description coverage, the description carries the burden. 'Self-declared' and 'without fetching evidence' give meaning to the categories levels and the evidence_url field (recorded but not verified). However, it doesn't explain the four enum levels, the scoring semantics, or agent_name's role beyond its name.

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 ('scores') and a precise resource ('eight self-declared continuity capabilities'), and the negative constraints ('without fetching evidence or invoking a model') give it a distinctive behavioral signature. The action clearly separates it from sibling tools that create, get, or register.

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

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

No explicit when-to-use guidance and no alternative tools are named. The negative constraints imply a use case — quick deterministic scoring of self-reported capabilities without verification — but the agent must infer it rather than being told.

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