astrondesign

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

No annotations are provided, so the description carries the full behavioral burden. It does not explain whether the tool generates/draws output, how the seed or redraw parameters affect results, whether it is read-only, or what the response looks like; it only states scope and exclusions.

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-loads the main scope before the exclusion. The wording is slightly awkward ('Deal an art direction') but there is no wasted text.

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 11 parameters, no annotations, no output schema, and no parameter descriptions, the definition is far too sparse. An agent would not know how to use the input fields or what behavior to expect from a creative-generation 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?

There are 11 parameters with 0% schema description coverage, and the description explains none of them. Terms like 'have', 'keep', 'list', 'seed', 'tone', 'brief', 'redraw', 'sector', 'options', 'sections', and 'direction' are left entirely for the agent to infer.

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 identifies a specific creative output: an art direction for a public landing or marketing page. It also excludes dashboards and app screens, which clarifies scope. However, the verb 'Deal' is nonstandard and it does not differentiate itself from sibling tools such as design_guide or design_render.

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 context: public landing or marketing pages, explicitly excluding dashboards and app screens. It does not name sibling alternatives or explain when to choose design_direction over design_search, design_guide, or design_render.

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?

No annotations are provided, so the description carries the full burden. It discloses that this is a guide/reference resource and hints at structured content (conflict precedence, critique protocol), which implies a read-only retrieval, but it never states the return shape, whether the guide is paged, or how large the payload is.

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 compact sentences, with the tool's identity front-loaded and the usage instruction trailing. The parenthetical reference list (impeccable, taste, UI UX Pro Max, brand DESIGN.md) is slightly noisy but does signal the scope of content covered.

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 guide tool with no annotations and no output schema, the description covers the entry-point case but leaves offset paging and topic-scoped retrieval behavior unexplained. Adequate to start, not enough to invoke correctly on subsequent calls.

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. 'Call first without topic' usefully tells the agent that topic is optional and should be omitted on the initial call, but the offset parameter (paging) is never mentioned, leaving half the parameters undocumented anywhere.

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 the resource (a UI/UX design harness guide) and enumerates its content: workflow, conflict precedence, critique protocol, and references. An agent can tell this is the documentation/entry-point tool rather than a search or render tool, though the wording is noun-phrase heavy and lacks an explicit verb like 'returns' or 'loads'.

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?

'Call first without topic' gives an explicit, actionable usage instruction that routes the agent to this tool before the siblings. It does not name the alternatives (design_search, design_direction) or state when a topic-scoped call is warranted, so guidance is clear but not complete.

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?

No annotations are provided, so the description carries the full burden. It discloses returned artifacts (HTML, 16 computed styles, bounds, crop) and that it writes a Design Feedback note, but omits permission/auth requirements, whether the note write is persistent or destructive, and the behavior of allow_network and inline_image.

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; the parenthetical lists outputs efficiently with no filler. Density compresses several behaviors into one line, but the sentence remains 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?

For an 8-parameter tool with nested objects, no annotations, and no output schema, the description is too thin. It does not explain the notes structure or network/image options, leaving important call-shaping details 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 0% for 8 parameters. The description names selector, point, and implies notes/crop, but leaves target, notes[].intent, allow_network, inline_image, and width/height unexplained, so it only minimally compensates.

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 ('Inspect') and resource ('page elements'), and names the two targeting modes (selector or point) plus what it returns. It does not explicitly differentiate from siblings like design_render or design_lint, so it is clear but not fully sibling-aware.

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 'by selector or point' hints at invocation modes but gives no when-to-use conditions, prerequisites, or comparison with sibling tools such as design_lint or design_search. There are no exclusions or alternatives.

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 no annotations, the description carries the full burden, and it does disclose one genuinely useful trait: 'Writes nothing to the project' tells the agent this is a non-mutating read. Beyond that it is silent on what a run produces (findings? pass/fail?), whether it needs configuration, and how the two engines combine.

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 compact sentences, front-loaded with the core action and with no filler. The only inefficiency is the opaque 'AstronDesign precedence' clause, which occupies space without conveying meaning to an outside agent.

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 tool with five parameters, two of them required, a required enum, no annotations, no output schema, and zero schema descriptions, the definition is far too thin. An agent cannot determine what surface values mean or what a lint run returns, so it is not complete enough to call confidently.

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 five parameters, so the description must compensate and largely does not. 'Source files' loosely maps to paths and 'impeccable and taste rules' to engines, but the required surface enum (persuade/operate/read/experience), allow, and design_md are never explained in either place.

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: static UI design lint of source files, with the two rule engines (impeccable, taste) named. That distinguishes it from siblings like design_render or design_inspect, though the phrase 'resolved by AstronDesign precedence' is unexplained jargon that adds no clarity.

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 says what it is but never when to pick it over design_inspect or design_guide, nor what preconditions exist (e.g., a design spec must already exist). No exclusions or alternative routing are given, leaving usage entirely 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?

No annotations, so the description carries the full burden. It usefully discloses two behavioral traits — headless real-browser rendering and that external network is blocked by default — but omits cost/latency, permission needs, and what allow_network changes.

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 dense sentence with the core capability and outputs front-loaded. No filler, though it could have spent a few more words on the high-value undocumented parameters.

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?

A 9-parameter render tool with no annotations and no output schema needs more explanation than this. The description names outputs but leaves most parameters and the composite result shape unexplained.

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 9 parameters and 0% schema description coverage, the description explains almost nothing. 'Several widths' and 'external network blocked by default' gesture at widths and allow_network, but target, surface, checks, wait_ms, design_md, allow, and inline_image remain undocumented.

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 ('Render') and resource ('a page in a real headless browser') plus the concrete artifacts produced (screenshots, measured design rules, accessibility snapshot). An agent can tell this is a visual render/eval tool, though it doesn't explicitly distinguish itself from sibling design_inspect or design_lint.

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 use this versus design_inspect, design_lint, or design_search, and no prerequisites beyond the network note. The outputs imply the use case but there is no explicit guidance or exclusion.

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?

No annotations are supplied, so the description carries the full disclosure burden. It correctly warns that output is advisory rather than prescriptive, which is useful, but it never states whether the tool is read-only, whether the "build a design-system" path writes or persists anything, or how broad results are. "Build" in a no-annotation context is an unresolved mutation ambiguity.

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 short sentences, front-loaded with the verb and the resource categories, with no filler. The size is right; the problem is missing content rather than verbal bloat, so it earns credit for structure while still being under-specified.

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?

A six-parameter tool with one enum, zero annotation coverage, and no output schema needs a description that explains modes, parameters, and result shape. This one covers none of that, leaving the agent to infer the mode switch and the meaning of most inputs.

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% across six parameters, so the description must compensate and largely does not. It loosely gestures at the domain enum (styles, palettes, fonts, UX rules) and at the design_system flag, but stack, project_name, max_results, and the other enum values (chart, landing, product, icons, gsap, react, web) are entirely undocumented anywhere.

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 verb ("Search") and concrete resource types (styles, palettes, fonts, UX rules), which is more than a tautology. But it presents a second, different operation ("or build a design-system suggestion") without explaining what selects that mode, and it never distinguishes itself from siblings like design_guide or design_direction.

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?

There is no when-to-use guidance, no exclusions, and no mention of the five sibling tools with which it overlaps (design_guide, design_direction, design_inspect). Is this for lookup or for full design-system generation? The agent has to guess. The only guidance-like line ("Results are recommendations, not rules") is about trust, not selection.

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