TokenOS dApp Builder

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond them: the call produces a spec plus a pre-filled IDE link rather than creating anything, and it constrains input provenance to the user's own words. It stops short of noting whether credits are actually consumed or whether repeated calls with the same idea return identical specs.

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, front-loaded with the purpose and followed by the calling constraint. The parenthetical output enumeration is long but each item is informative, and no sentence is wasted; slightly tighter phrasing would earn a 5.

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 an unusually good job of describing the return artifact by listing the spec sections and the IDE link. The remaining gap is the optional parameters: an agent cannot tell from the description whether passing 'chain', 'style', or 'features' pins those spec fields or merely hints at them.

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 5 parameters and only 40% schema description coverage, the description should carry more weight, but it only reinforces the required 'idea' parameter (which the schema already documents) and is silent on 'name', 'chain', 'features', and how optional inputs interact with the generated spec. The 'chain' enum values are never mentioned, so the description does not compensate for the coverage 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 states a specific transformation (user's app idea → spec) and enumerates exactly what the spec contains: features, pages, components, data model, Web3 integrations, stack, steps, credit estimate, plus a pre-filled TokenOS IDE link. No sibling (recommend_models, tokenos_capabilities) overlaps with this planning role, so an agent can route to it unambiguously.

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?

Explicit when-to-call and when-not: 'Only call with the user's own description' and, if the request is vague (e.g. 'build an app'), ask the user what the app should do and for whom first. It also states a hard prohibition — 'never invent an idea' — which is the exact failure mode an agent would otherwise commit.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description adds that results come from a 'live TokenOS roster' and include 'price multipliers,' which is useful output context, but says nothing about ordering logic, freshness, or result 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?

One front-loaded sentence with no padding. The modifier stack 'best, balanced and cheapest' is slightly muddled since those criteria can conflict, but the sentence remains compact and readable.

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 partially compensates by hinting returns include price multipliers, but does not describe the recommendation structure or ordering. For a low-complexity, single-optional-parameter tool with rich annotations, this is adequate but not complete.

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

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

Schema description coverage is 0% for the single 'task' parameter, so the description must carry the burden, and it only loosely implies the parameter is a build-task description. It gives no format, expected content granularity, or note that the parameter is optional despite being the only input.

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 verb 'Pick' and resource 'models' are specific, and the scope ('best, balanced and cheapest frontier models from the live TokenOS roster for a build task') is concrete. It does not, however, differentiate itself from the siblings plan_dapp or tokenos_capabilities, so an agent cannot tell from the text alone when this is preferable to those.

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?

'for a build task' implies the usage context, so the when-to-use is inferable. There are no exclusions, prerequisites, or named alternatives (plan_dapp, tokenos_capabilities) to route the agent, leaving the choice between siblings to inference.

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 establish readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds no behavioral context beyond that – no return format, size, or freshness information – leaving it as a bare category list.

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 prefixed with 'Reference:' that wastes no words. Appropriately sized for a no-parameter informational tool.

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-param read-only reference tool this is minimally adequate: it names the covered domains but gives no depth on what each entry contains or how to use the results when feeding into plan_dapp or recommend_models.

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 per the baseline there is nothing for the description to document. No compensation is required.

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

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

The description enumerates topic categories (chains, deployment targets, hosting, token launch, agents, payments, credits) which gives a rough sense of scope, but there is no verb and no explicit statement of what the tool actually returns. It does not distinguish itself from siblings plan_dapp or recommend_models.

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 offers no when-to-use guidance, no conditions, and no mention of alternatives. The agent is left to infer that this is a lookup to consult before planning.

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