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

Annotations already declare readOnlyHint and idempotentHint, yet the description adds substantial context beyond them: it does not trigger interactions, so "observed" is normally absent, and `gaps` distinguishes "could not read" from "declares no interactions." That last point is exactly the kind of failure-mode disclosure annotations cannot carry.

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-loaded with the purpose, then the confidence taxonomy, then the gap semantics, then the one actionable toggle — the ordering is deliberate. Slight redundancy in restating the facts-only view, but every section carries information an agent needs before trusting the output.

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?

Output schema exists, so return shapes need not be explained, yet the description covers the interpretive burden the schema cannot: what each confidence level means and how to read an empty result with a gap. Nothing needed to call it correctly or interpret it 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 coverage is 100%, so baseline is 3, but the description adds real meaning to includeInferred by tying it to the confidence taxonomy and explicitly recommending it stay on. The `page` and `format` parameters are left entirely to their schema text, keeping it below a 5.

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: "Report which widgets on an Axure page respond to user input, and what each one does," then enumerates the action and trigger vocabulary. The evidence-level framing makes the scope distinct from a page map or a visual capture, so an agent can tell it apart from axure_get_page_map or axure_get_visual without reading 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?

Gives one concrete usage instruction ("Set includeInferred=false for a facts-only view") and a safety statement ("does not click, type or change page state"). However it never names an alternative sibling such as axure_get_page_map or axure_get_visual, nor states when-not to use it, so the routing decision is left partly 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 readOnly/openWorld/idempotent, but the description adds non-obvious traits: it does not click, type or navigate, and its output is explicitly untrusted data rather than instructions. It also discloses that a stats line reports omitted nodes and why, which directly affects how an agent should interpret a truncated result.

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-loaded with what is returned, then scoping, then the read-only/untrusted caveat — a sensible order. Slightly long for the payload, with a few sentences echoing schema defaults (detail levels, coordinate space).

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 13-parameter tool with an output schema, it covers the things the schema cannot: why to scope a dense page, how to pair with the visual sibling, and the trust boundary on returned page content. Nothing an agent needs in order to call it correctly is absent.

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 every parameter including defaults and ancestor-retention behavior. The description mostly restates this (canvas pixels by default, standard detail level); its one genuinely additive point is the viewport/axure_get_visual pairing. 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 ('Open one Axure prototype page') and enumerates exactly what comes back: widget id, kind, geometry, text, plus fill/border/radius/opacity at standard detail. It also carves out a clear boundary against siblings by noting the viewport mode 'pairs with axure_get_visual for the same page.'

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 real guidance on how to use it at scale ('pass region or widgetIds to focus, and maxNodes to bound') and routes between output modes ('prefer standard when another agent will reason over the result; prefer outline for a compact structural listing'). What's missing is an explicit statement of when to choose axure_get_visual or axure_get_interactions instead — the pairing is mentioned but not the selection rule.

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/openWorld, yet the description adds real behavioral context: the screenshot comes from the live prototype and should be treated as untrusted data, text-only models get only geometry plus a note, savePath writes the PNG for a separate vision step, and geometry is returned alongside pixels. This meaningfully extends beyond the structured safety 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 purpose is front-loaded in one sentence, then each paragraph handles one concern: target modes, image/model handling, and data trust. No filler; every sentence conveys an operational fact an agent needs.

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 an output schema, full annotation coverage and 100% schema description coverage, the description fills only the gaps structured data cannot: which target mode to choose, how text-only models are handled, and that the image is untrusted design data. 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?

With 100% schema coverage the baseline is 3, and the description adds meaning on top: it clarifies that per-widget geometry is reported individually, that 'none' suppresses the image entirely, and that includeImage=false still returns canvas size and regions. Most parameter detail (pad clamping, savePath sandboxing, scale having no effect) is already in the schema, so it does not add much further disambiguation.

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 opening sentence states a specific verb and resource: it captures pixels from an Axure page and returns them with the geometry of exactly what was captured, tied to axure_get_page_map coordinates. The second paragraph then enumerates each target mode (full-page, widgets, viewport, none) so an agent can distinguish the variants without opening the 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?

It explicitly says which target to pick and why: full-page for layout, spacing and hierarchy; widgets for reading a single table, card or dialog; none for geometry only. It also gives a when-not condition for images via includeImage=false for text-only models or tight context. It names a sibling only implicitly (axure_get_page_map for coordinate alignment), so no explicit alternative routing is 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 already declare readOnlyHint, openWorldHint, and idempotentHint, so safety behavior is covered. The description adds useful behavioral context: it is a cheap navigation step and the response begins with an untrusted-data notice, which is important for handling prototype-derived text.

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 short and front-loaded: the listing action and return shape come first, followed by when to call it and the untrusted-data warning. Every sentence adds useful information without 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?

Given annotations, an output schema, and complete schema coverage, the description provides everything needed to select and invoke the tool correctly. It covers purpose, usage timing, downstream handoff, and the important untrusted-data notice.

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 filter and refresh parameters are already fully documented in the schema. The description does not add meaning beyond the schema for those parameters, so the baseline of 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 states a specific verb and resource: list Axure prototype pages as a folder tree, including page ids and URLs. It distinguishes the tool from siblings by explaining that returned page ids feed directly into axure_get_page_map or axure_get_visual.

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 clear usage condition: call this first when you do not know which page to analyse. It does not explicitly state when not to use it, and the named siblings are downstream consumers rather than alternatives, but the intended 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 only flag readOnly=false, openWorld=true, idempotent=true; the description adds materially — session-persistent effect, server-side verification against the live Axure runtime, refusal of metadata endpoints/embedded credentials/non-web ports, and the fact that a failed verification admits nothing. Slight gap: it does not say how to revert to the configured AXURE_URL or whether a prior override is replaced silently.

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-loaded with the core action, then when-to-use, then safety, then post-call state; each paragraph carries distinct information. Mildly verbose in the safety paragraph ('looking for the Axure runtime in the real page'), but nothing is pure filler.

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?

An output schema exists, so return values need not be fully restated, yet the description still previews the useful payload (Axure signals, page count, bounded page list) and points to axure_list_pages via the schema for the rest. Safety, failure behavior, session lifetime and next-step usage are all covered.

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; the description still adds genuine semantics for `url` — untrusted-input handling, http(s)-only requirement, and pre-admission verification — beyond the schema's own note. The other four parameters (filter, maxPages, settleMs, viewport) are covered only by the schema, which is acceptable given full 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?

States a specific action — repointing the server at a different Axure prototype — and explicitly scopes it as 'without changing any configuration', which cleanly separates it from the read-only siblings axure_list_pages, axure_get_page_map, axure_get_visual and axure_get_interactions.

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 an explicit trigger ('when the user names a prototype address in the conversation') with a concrete example, plus a named exclusion ('Do NOT call this when the user names no address') and the failure mode of guessing. The follow-up instruction ('then call the other tools normally') tells the agent what to do next.

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