Screenrove

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavioral context on top: the exact payload assembled into the prompt and the includeDesign=false escape hatch for teams with their own design system. It stops short of saying how large the prompt can get or whether screens are truncated.

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 the artifact contents front-loaded and the accepted id forms trailing, which matches how an agent reads. The content list is long but each item earns its place by defining the output. Only minor trimming is possible.

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 carries the burden of describing the return payload, and it does so concretely. Combined with annotations covering the safety profile and a fully documented 5-parameter schema, an agent has nearly everything needed; only edge cases like large reference sets or truncation go unmentioned.

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% so the baseline is 3, but the description adds the referenceId naming grammar ({product}-onboarding, {product}-collection, single screen id) that goes beyond the schema's flat example list, clarifying the accepted id families. Other parameters (goal, stack, screens, includeDesign) are only covered by 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?

Names a specific verb and artifact (build a handoff prompt) and enumerates exactly what the artifact contains: ordered screens with notes, observed transitions, image URLs, design guide, checklist. That composite output is distinctly different from what siblings like get_design or get_screen return, so an agent can route correctly without opening any schema.

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 second sentence tells the agent what to pass as referenceId (an onboarding flow, a whole collection, or a single screen id), which is really input guidance. It never says when to choose build_handoff over check_my_ui, get_design, or get_product, nor when not to use it. Usage is implied by the described output rather than 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?

Annotations only declare readOnlyHint and openWorldHint=false. The description adds meaningful behavior the annotations cannot convey: a hard privacy constraint ('Do not send the image, and leave out real names, emails, prices or customer data: structure only') and the return shape ('short report with the closest references (the best match's screenshot attached)').

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, front-loaded with the core action, then the procedural constraint, then the return value and next step. No sentence is filler; the 'structure only' warning is placed right where the agent needs it before filling fields.

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 10-param, no-output-schema tool the description covers purpose, the privacy-critical authoring procedure, the returned report contents, and the follow-up handoff to pickReference. Nothing an agent needs to invoke it correctly 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?

Schema description coverage is 100%, so the baseline is 3 and the 10 field descriptions already carry the per-parameter meaning. The description adds the governing philosophy behind those fields — describe the structure in them, structure only, no PII — which clarifies how they should be filled beyond the raw schema text.

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 ('Find the real product screens closest to the user's own screen or flow and compare them') and names the exact comparison dimensions (step counts, plan counts, page sections). It is clearly distinguishable from siblings like search_screens or get_screen by its compare-the-user's-own-UI framing.

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?

Gives explicit ordering ('First look at the user's screenshot or running app yourself, then describe its structure in these fields') and a routing rule to a named sibling ('pass their ids to pickReference') for the chained workflow. The condition that selects the next tool is spelled out, not left 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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that the two surfaces are measured independently, which is genuinely useful behavioral context, but says nothing about response shape, caching, or what happens when the requested surface has no measurements.

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, no filler: the first defines the return payload and the second front-loads the key splitting behavior. 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?

For a two-parameter, read-only lookup with full schema coverage and no output schema, the description covers what the tool returns and how the surfaces divide. Minor gaps remain around error cases (unknown productId) and result shape, but nothing essential to correct invocation 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?

Schema description coverage is 100%: both parameters are fully documented in the schema, including the enum meaning and the productId example set. The description's remark that surfaces are measured separately restates the context parameter's semantics rather than adding new syntax or constraints, so the 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 ('Get the measured design guide for a product') and enumerates the contents (font, palette, type scale, layout, component notes), so the agent knows exactly what comes back. It does not explicitly contrast itself with siblings like check_my_ui or build_handoff, so it falls short of a 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 note that 'marketing site and product UI are measured separately' implies when the context parameter matters, and the schema points to listProducts for the id. However there is no explicit when-to-use/when-not guidance or routing against alternatives such as pick_reference or get_screen, leaving the agent to infer the boundary.

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 and openWorldHint=false, so safety is covered. The description adds genuine value beyond that by disclosing the shape of what comes back (coverage notes, design summary, screens bucketed into onboarding/marketing/in-product), which annotations cannot express.

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 that names the resource first and then the contents, with no filler or repetition.

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, single-parameter tool with no output schema, the description does the heavy lifting by summarizing the return structure and its grouping. It stops short of error/permission behavior, but nothing essential to invoking the tool 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?

Only one parameter and schema coverage is 100%, with example ids (linear, stripe, airbnb) already in the schema. The description adds no further parameter meaning, so the 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 ('Get') and resource ('a product') and enumerates the payload: coverage notes, design summary, and every screen grouped into three categories. It is clearly distinct from the plural list_products sibling, though it never names that sibling to steer selection.

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 productId schema text ('Product id from listProducts') hints at the list-then-get sequence, but the description itself gives no when-to-use guidance and names no alternative such as get_design or get_screen.

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 and openWorldHint=false, so safety is covered. The description adds genuinely useful behavioral context by enumerating the returned payload, which matters because no output schema exists. It omits edge behavior such as a bad/unknown screenId.

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, front-loaded with the verb and resource, followed by a compact enumeration of contents. 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?

With no output schema, the description usefully enumerates the return contents, and annotations cover the safety profile, so an agent has what it needs to call this. Only minor gaps remain (invalid-id behavior, size of 'everything' for long pages).

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 screenId description already gives the source ('from searchScreens or getProduct') and an example. The description adds nothing beyond the schema, so the 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 ('Get') plus resource ('one screen') with an explicit inventory of what is returned: notes, source URL, image URLs/dimensions, observed actions, and page sections. This clearly separates it from siblings like get_screen_image or search_screens.

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 enumeration of contents; there is no explicit statement of when to call this versus get_screen_image or search_screens, nor any prerequisite or follow-up 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 readOnlyHint and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond the annotations: the 4000px threshold where preview truncates, and the warning that size=full may exceed what vision models can accept.

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?

Front-loads the core action in the first sentence, then adds scoping and vision-limit caveats. Three sentences, all earning their place, with no redundant restatement of the schema enum.

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 explains what comes back (the image) and its practical limits, plus the sibling that supplies section metadata. Adequate for an image retrieval tool with full schema coverage, though return format details (e.g., resolution/type) are not addressed.

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%, so the baseline is 3, but the description adds meaning the schema lacks: preview yields only the first screen above the fold, and full returns the whole page at the risk of exceeding vision-model input limits. The size tradeoff is therefore clearer than the schema alone.

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 ("Get the screenshot itself") and immediately distinguishes itself from the metadata-oriented sibling by noting that getScreen returns section y-offsets instead of the image. An agent can tell what this returns versus neighboring tools without opening a schema.

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?

Gives concrete guidance on when to pick preview vs size=full (above-the-fold vs whole page, vision-model limits) and routes section-level needs to getScreen. It stops short of an explicit "when to use this tool instead of get_screen" statement, but the context is clear.

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 and openWorldHint=false, so the safety profile is covered. The description adds value by specifying the fields returned (capture date, tags, coverage notes, screen counts), which matters because there is no output schema. It stops short of noting ordering, pagination, or empty-library 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?

Two sentences, no filler, with what the tool returns front-loaded ahead of the usage hint. 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 zero parameters and no output schema, this is a simple read-only list tool, and the description compensates for the missing output schema by naming the returned fields. Ordering, pagination, and count limits are unstated, but for a discovery endpoint the definition is largely sufficient.

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 no parameters, so the baseline is 4. The schema is empty and there is nothing for the description to clarify; it correctly makes no parameter claims.

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 and resource ('List every product in the library') and enumerates the data returned (capture date, tags, coverage notes, screen counts). It implies differentiation from get_product by positioning itself as the entry point, but never names a sibling 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?

'Start here to see what references exist' gives an implied usage context as a discovery entry point, which is useful. However, it offers no explicit when-not guidance or named alternatives (e.g. get_product for a single product, search_screens for filtering), leaving routing 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 declare non-read-only, non-idempotent behavior but say nothing about what actually happens; the description fills that gap by disclosing that it returns a url, that the agent must open it in a browser, and that a follow-up call to wait_for_pick with the pickId is required. It does not cover failure modes (e.g., no matches) or how long the pick remains valid.

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?

Front-loads what the tool does and where the output goes, then the required follow-up step; no filler sentences. The final sentence is dense but every clause (returned url, per-OS open command, waitForPick handoff) 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?

With no output schema, the description correctly explains the return value (a url plus pickId) and the end-to-end interaction protocol across two tools. It omits edge cases such as zero matches or user abandonment, which for a 7-parameter interactive tool is a modest but real 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?

Schema coverage is 100%, so the schema already documents q, goal, kind, count, stack, product, and screens. The description adds only loose hints ('a few matching references' for count, 'instead of searching' for screens) and no syntax or format detail, so the baseline 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?

States a specific verb and resource ('show the user a few matching references side by side ... let them click the one to build from'), and explicitly contrasts itself with an alternative flow ('prefer this over sending full-page images'). An agent can distinguish it from get_screen_image and search_screens without opening a schema.

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?

Gives a clear selection condition ('whenever the user should decide') and names the alternative it should replace (full-page images). It does not spell out when not to use it versus search_screens or how to handle a no-match result, so it falls short of full when/when-not coverage.

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 and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: it discloses the four fields searched and confirms the whole captured corpus is scanned, which tells the agent what recall to expect.

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 core action and scope, with the filtering and example-query detail following. No filler, though the second sentence's three examples are slightly padded.

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 keyword search with no output schema and full schema coverage on 4 optional parameters, the description supplies what an agent needs to select and call it. It omits any note on result ordering or return shape, but those are marginal 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%, so every parameter including the q-omit behavior, limit range, and product id example is already documented in the schema. The description's "Filter by product or kind" restates schema content rather than adding syntax or semantics, so the 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 and resource ("Search every captured screen") and scopes the search surface to titles, notes, page sections, and observed actions. It implicitly separates itself from get_screen/get_screen_image by being a keyword search rather than an id lookup, but it never names those siblings, so the differentiation is left to inference.

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 concrete usage context with example queries ("pricing page", "empty state", "date picker") and states the two filter axes (product, kind). It does not state when to prefer a different sibling (e.g., pick_reference or get_screen), so there are no explicit 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?

With readOnlyHint=true already declaring the safety profile, the description adds real behavioral detail: the call returns immediately on click, otherwise yields a pending status, and the successful return includes a reference, screenshot, and build prompt. It does not mention timeouts or what happens if the user never picks, but the polling behavior is disclosed.

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 short sentences, front-loaded with the core action and immediately followed by the polling rule and the return payload. No filler, though the mid-sentence 'or status pending after the wait' is slightly clunky.

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 burden of explaining returns (reference, screenshot, build prompt) plus the pending-status case. It is sufficient for an agent to call and interpret this tool, missing only edge cases like timeout/failure behavior.

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 both the wait duration (0-50s) and pickId provenance are already documented in the schema. The description adds no meaning beyond that, which is the expected baseline when the schema does the heavy lifting.

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 (wait) and resource (the user's choice on the pick page), and clarifies that it blocks until the click. It is clearly distinguishable from sibling pick_reference, which creates the pick that this tool awaits.

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 clear usage context: call it with the pickId from pickReference, and re-call it if the result is status pending. It does not explicitly name an alternative or a when-not condition, but the polling contract is spelled out well enough to drive correct invocation.

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