PromptUI

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

Goes well beyond the annotations by disclosing that the build is asynchronous, that it consumes credits from the authenticated account, and that the immediate response is a buildId rather than a finished app. Those are the operational facts an agent most needs for a non-idempotent, open-world, credit-spending call.

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 zero filler: the action and cost/async contract come first, the next-step pointer second. Every clause carries actionable 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?

Despite having no output schema, the description states what is returned (buildId) and how to get the eventual result (poll get_build_status), so an agent can complete the full loop. Nothing material is missing given that annotations carry the safety profile and the schema carries parameter detail.

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 mode, framework, prompt, and _confirmed are already documented inline, including enum values and defaults. The description adds no additional parameter meaning, so 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?

Specific verb+resource with product context ('Build a working web app ... with PromptUI') and an explicit boundary against the sibling deploy_app by framing this as the build step. It also names the return value (buildId), so an agent can distinguish it from list_builds/get_build_status without opening schemas.

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?

Explicitly routes follow-up to get_build_status for progress and the preview link, which is the key orchestration guidance. It lacks an explicit 'when not to use / use deploy_app instead' exclusion, which is the only missing piece.

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?

Beyond the annotations (openWorldHint=true, idempotentHint=true, destructiveHint=false), the description discloses the cost model — first deploy charged, redeploys free — and a non-obvious failure path where the tool returns free-trial instructions instead of deploying. It omits that a `_confirmed` user approval is required for this credit-spending write, which the schema covers but the prose does not reinforce.

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 tight sentences with no waste: what it does first, the cost consequence second, the plan fallback third. Every sentence earns its place and nothing repeats the schema verbatim.

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 covers the main non-success return (trial instructions instead of a deploy) and the prerequisite, which is what an agent needs to avoid misusing it. Only the confirmation requirement for spending credits and the shape of a successful response (the live URL) are left implicit via the title.

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 buildId description already specifies 'a completed build,' so the schema carries the parameter burden. The description's reference to 'a completed PromptUI build' adds only marginal reinforcement and says nothing about `_confirmed`.

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 first sentence gives a specific verb and resource: 'Deploy a completed PromptUI build to a live URL.' The 'completed build' prerequisite implicitly separates it from build_app, though no sibling is named explicitly.

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 by the 'completed build' qualifier and the plan/trial fallback phrasing, but the description never names build_app or another alternative, nor does it state exclusions such as what to do if the build is incomplete.

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, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds that the input is returned verbatim, which tells the agent the response shape, but nothing about output format beyond that or error behavior on missing input.

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 short sentence with no filler; the purpose is front-loaded immediately after the action. Nothing wasted.

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 diagnostic tool with complete annotations, the description is nearly sufficient. Only a note on what the response looks like (plain echoed string vs. envelope) is missing, and that is minor here.

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% with a single required 'message' string, so the schema carries all parameter meaning. The description adds nothing about the parameter beyond restating that the input is echoed, which earns only the 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 (echo) plus resource (the input) and an explicit purpose clause ('for testing MCP integration') that cleanly separates it from the app-building and GTM siblings. It stops short of naming a sibling, but the intent is 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?

'For testing MCP integration' implies the usage context, but there is no explicit when-to-use/when-not guidance or reference to alternatives. For a diagnostic tool that is largely sufficient, though it leaves the agent to infer that it should not be used in real workflows.

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 cover the safety profile (readOnly, idempotent, non-destructive), so the description is free to add real value — and it does, by enumerating the four terminal/intermediate return states including previewUrl on success. It stops short of noting what an agent should do on needs_clarification or whether repeated polling is expected.

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 clauses, both front-loaded: purpose first, then the enumerated outcome states. No filler and nothing repeated from the schema verbatim.

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 correctly takes on the job of describing return states, and does so. It is slightly incomplete for a polling tool — it doesn't say whether states are transient, how often to re-check, or what to do when the result is needs_clarification.

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 buildId description already says 'returned by build_app', which the tool description echoes. Baseline 3 applies: the description adds no format or provenance detail beyond the schema.

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 ('Check the status of a PromptUI build') and anchors it to the producing tool ('started with build_app'). It doesn't distinguish itself from sibling list_builds, which an agent could plausibly confuse with a single-build status lookup.

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?

Naming build_app establishes the natural workflow context (build then poll), which is useful implied guidance. However, there is no explicit statement of when to use this versus list_builds, nor any guidance on polling/when to stop.

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 this as a non-read-only, non-destructive, non-idempotent write operation. The description adds that the draft is persisted for the authenticated user, which is useful context, but it does not mention credit spending, the required _confirmed approval, or what happens on repeated calls.

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, front-loaded sentence with no wasted words. It is appropriately concise, though it could carry slightly more operational context without becoming bloated.

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 nine-parameter generation tool with no output schema, the description is minimal. It does not explain that this creates a draft rather than publishing it, nor does it mention the approval gate implied by _confirmed, which is important context for a write/credit-spending action.

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 all nine parameters are already documented in the schema, including count, channel, deliverable type, and _confirmed. The description adds no parameter-level meaning beyond the schema, so the baseline score of 3 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 uses a specific verb phrase, 'Generate and persist a new GTM content draft,' and scopes it to the authenticated user. It clearly identifies the resource as a content draft, which distinguishes it from gtm_publish_content and gtm_list_content, though it does not explicitly name or contrast with siblings.

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 explicit when-to-use guidance, prerequisites, or alternatives. It does not say when to choose this over gtm_publish_content, gtm_list_content, or other content-related 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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds real behavioral context: results are workspace-scoped, attribution is deliberately separated from causal claims, and missing spend/cost data is surfaced rather than fabricated. It stops short of describing the response shape, which matters since there is no output schema.

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 with the verb and scope front-loaded and no filler. Density is high, though terms like "PromptUI GTM" and "verified commerce outcomes" assume context an agent may not have.

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 tool with no output schema, the description conveys what the result covers (channel analytics, commerce outcomes) and how to interpret it (attribution ≠ causality, explicit coverage gaps). What is missing is any sense of the return structure or granularity, which the absent output schema leaves entirely on the description.

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 for the description to disambiguate; baseline applies. Nothing in the text conflicts with the empty schema.

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 concrete verb ("Read") and names the resource precisely: PromptUI GTM channel analytics plus workspace-scoped verified commerce outcomes. It is distinguishable from all siblings (build/deploy/content tools) because no other tool touches analytics, though it never explicitly states that differentiation.

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 by the phrase "current ... analytics" — there is no statement of when to call this versus gtm_list_content or web_scout, and no prerequisites or exclusions. The caveat about attribution vs causality is an interpretation note rather than routing 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, so the safety profile is fully covered. The description adds the useful constraint that results are scoped to the authenticated PromptUI user, but says nothing about ordering, pagination behavior, or what a queue item 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?

A single front-loaded sentence with zero filler or repetition. It is arguably too terse for the information an agent needs, but nothing in it is wasted.

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 no-required-parameter read-only list with a fully documented schema, rich annotations, and no output schema to explain, the description covers what is needed to invoke it correctly. The remaining gaps (ordering, default sort) are minor for this tool class.

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% with defaults and enumerated valid values documented per parameter, so the schema does the heavy lifting. The description adds no meaning beyond it, which is the expected baseline when coverage is complete.

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 ("List GTM queue items") and scopes it to the authenticated user, so the agent knows it is a read over the user's own content. It does not differentiate from siblings like gtm_publish_content or gtm_generate_content, and "queue items" is not obviously the same resource as the title's "marketing content".

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 statement of when to call this versus alternatives (e.g. fetch a single item, generate, or publish), and no prerequisites beyond an implicit need to be authenticated. The agent must infer usage entirely from the name and schema filters.

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=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds nothing beyond restating the purpose: it doesn't say posts go live irreversibly, that publishing may consume credits, or what happens when a target id is omitted.

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. It is efficient, though the brevity is a symptom of under-specification rather than disciplined editing.

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 5-parameter, non-idempotent, open-world write action with no output schema and a user-approval gate, the description omits outcome expectations, failure modes, and the confirmation requirement. An agent cannot tell from the description alone what a successful publish implies.

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 every parameter including contentId, platform override, and page/IG targets is documented in the schema. The description adds no meaning beyond that baseline, which is acceptable but not additive.

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: publish one GTM content item to a connected social platform. This distinguishes it from siblings like gtm_generate_content and gtm_list_content, which create and enumerate rather than publish.

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 guidance on when to use this versus alternatives, no prerequisites such as needing an already-connected channel, and no mention of the confirmation gate required by _confirmed. The agent must infer everything from the schema.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that results include statuses, but says nothing about ordering, recency window, pagination, or what to do when more builds exist than the limit.

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, zero redundancy, and the scope modifiers ('authenticated user's', 'recent', 'with their statuses') are front-loaded before the noun phrase.

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 single-parameter read-only list tool with full annotations and full schema coverage, the description tells the agent what it gets back at a high level. Minor gap: no mention of result ordering or what happens once the limit is hit.

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% and the single 'limit' parameter already documents default 10 and max 50. The description adds no constraint, ordering, or formatting detail beyond the schema, so 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?

States a specific verb and resource ('List ... PromptUI builds') and scopes it to the authenticated user's recent builds with statuses. It does not name a sibling such as get_build_status to draw the single-vs-list boundary explicitly, so it stays at 4.

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: the word 'recent' hints that this is for a recent-activity listing rather than a specific build, and 'authenticated user's' implies auth is required. There is no explicit when-to-use, when-not-to-use, or pointer to alternatives like get_build_status.

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, non-destructive, open-world behavior, so the safety profile is covered. The description adds meaningful context beyond that: it never installs anything, official upstream items require compatibility review and are not runtime verified, and it returns ready-to-use JS with correct imports. The note about 'bounded dependency/CSS/provenance information' also hints at inspect's output scope.

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 poorly front-loaded: it opens with action-level details before stating the tool's main purpose ('Get shadcn/ui component code pre-adapted...'), and the component list is repeated verbatim from the schema. Several sentences (e.g., 'Default action local retrieves...') are awkward and could be tightened.

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 tool with seven fully described parameters and no output schema, the description covers the actions, a key caveat about upstream items, and the return format at a high level. It still leaves gaps around pagination behavior for search, the exact shape of inspect results, and error handling, which an agent might need.

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 every parameter is already documented in the input schema, including the component list, action enum values, registry, and tailwindVersion. The description restates the component list and action meanings but adds no format or constraint details beyond the schema; baseline 3 is warranted.

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 names three concrete actions (local retrieves adapted components, search discovers the official catalogue, inspect reads source/provenance) and states the overall goal of getting pre-adapted shadcn/ui code for Sandpack. It distinguishes the actions internally but does not clearly differentiate the tool from siblings like build_app.

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 a directive ('Use this instead of building complex UI primitives from scratch') and implies when each action applies via their definitions. However, there are no explicit exclusions, no guidance against using build_app for the same purpose, and no prerequisites stated beyond the upstream compatibility caveat.

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, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful trait with no output schema present: results come back as markdown. It says nothing about latency, cost per page, failure modes for unreachable URLs, or how multiple pages are combined.

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 capability and closed with the return format; no filler. The middle clause is a short use-case list, which is efficient but reads more like examples than guidance.

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, stating the markdown return format closes the biggest gap, and the read-only/open-world annotations cover safety. Remaining omissions (per-page cost, behavior when a fetched URL fails, how many findings to expect) are minor for a three-parameter research 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 100%, so goal, urls, and maxPages are already documented, including the key search-vs-fetch branch ('if omitted, will search the web'). The description adds no format, syntax, or interaction detail beyond that, so 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?

The description names a specific verb set (search, read, fetch, verify) and a specific resource (the live web), then sums up the output ('structured findings as markdown'). An agent knows exactly what capability this tool provides without opening the schema, and no sibling tool (build/deploy/gtm/shadcn) overlaps.

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?

Concrete use cases are listed ('read documentation, fetch API references, verify library usage'), which implies when to call it, but there is no explicit when-not guidance and no named alternative for overlapping needs (e.g. local codebase lookups). Usage is inferred rather than stated.

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