Icons8

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

Annotations only cover readOnly/openWorld; the description adds substantial behavioral context beyond that: 'lottie' requires an Icons8 sign-in or personal API key while gif/apng need none, Lottie counts toward a paid-download limit, refusals carry 'retry_after_seconds', and unavailable sizes are refused rather than silently misreported. Credential and rate-limit disclosure like this is exactly what 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?

Well front-loaded and organized with a bolded sizing caveat and bulleted format selection, so it is easy to scan. It is nonetheless long for a 3-parameter tool, and the point that gif/apng links already come free is stated twice (once up top, once in the format list), which is mild 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?

Given an output schema exists, the description still helpfully documents return shapes (parsed Lottie JSON string, permanent credential-free url plus size, error objects). Auth requirements, failure modes, and the size-omission default are all covered, leaving nothing an agent needs to call this correctly.

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 only 33% (only icon_id documented), so the description carries the burden and does it well: format values and their auth/implications, and size semantics including that Gif/APNG render at fixed per-style sizes (with concrete examples), that size is ignored for Lottie, and that mismatched sizes are refused.

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 an animated icon's motion') and immediately names the returned formats (Lottie, GIF, animated PNG). It cleanly distinguishes itself from siblings get_icon_svg and get_icon_png_url by explaining that those return still frames for animated icons.

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 names the discovery path (search_icons(animated=True)), states the precondition (only isAnimated icons qualify, ~1 in 50), and tells the agent when NOT to use it (gif/apng links already come with animated hits, so use this for Lottie or sizing). It then gives per-format selection guidance for lottie vs gif vs apng with build context.

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 safe-read profile is covered. The description adds one genuinely useful behavioral caveat ('An animated icon's PNG is a still frame'), but does not disclose URL permanence, auth needs, or any other runtime behavior beyond that single note.

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?

Core guidance is front-loaded and useful, but the 'Args:' and especially 'Returns:' block duplicate information already present in the input and output schemas, and the 'ctx' arg is an internal detail that does not belong in an agent-facing description. Some trimming would sharpen it.

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 annotations covering the safety profile and an output schema covering return values, the description's job is to add selection and caveat context, which it does well. It is essentially complete for a simple URL-fetch tool; only minor details like URL lifetime are 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 description coverage is only 50% (icon_id documented, size not), so the description must compensate. It does: it explains size as 'The preview image size in pixels (default: 24)' and restates the icon_id source. Minor noise from mentioning 'ctx' as an argument that is not in the schema keeps this 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 ('Get a PNG URL for an icon by its ID') and immediately distinguishes itself from siblings by naming get_icon_svg as the preferred format and get_icon_animation for motion. An agent can select this tool 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?

Explicitly states when to use ('use when SVG is not available'), when not to ('SVG format is preferred ... use get_icon_svg'), and the alternative for animated content ('Use get_icon_animation for the motion'). Nothing is 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 cover the safety profile (readOnlyHint=true), and the description adds substantial non-obvious behavior: API key requirement, the still-frame caveat for animated icons plus the accompanying note/animation block, error surfacing, and the paid-download limit with retry_after_seconds and free PNG fallback.

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 and the format preference, and the behavioral caveats earn their space. The 'PREFERRED FORMAT' and 'RECOMMENDED' lines say the same thing twice, and the Args/Returns boilerplate is partly redundant with the schema and output schema.

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 paid, key-gated fetch tool this is complete: it covers the id source, error/limit behavior, and the animated-icon edge case. An output schema exists, yet the return-shape notes add value rather than padding.

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% for the single icon_id parameter, and the description only restates its provenance (icons[].id from search_icons) with no added format or syntax detail. Baseline 3 is appropriate when the schema fully carries the parameter.

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 (icon SVG) by ID, and explicitly frames itself as the preferred SVG format versus the PNG sibling. An agent can distinguish it from get_icon_png_url without opening either 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 an explicit recommendation ('Use this tool instead of PNG when possible') with the reason (quality/scalability), and names the source of the required id (search_icons results). The alternative is named and the selecting condition 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 only cover readOnlyHint/openWorldHint; the description adds the substantive behavioral facts: presigned URL expires in one hour, every format except gif-low requires a paid account, every format but gif-low counts toward the paid-download limit, refusals carry retry_after_seconds, and per-format caveats (mp4-hevc Safari-only, prores ~55MB mastering file, gif-low has no transparency). This is far beyond what annotations provide.

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 purpose and the critical 'animated only' constraint, and nearly every section earns its place given seven format values. It is nonetheless long, and the digression on upstream naming (mov-avc/mov-hevc) and the extended Safari canPlayType rationale carry more detail than an agent strictly needs to select and invoke the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, and the description still summarizes the return shape ({url, width, height, expires_in_seconds}) and the error shape including retry_after_seconds. Auth requirements, expiry, format availability variability, and browser-compatibility guidance are all covered, leaving no material gap for a two-parameter 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 coverage is 50% and the schema gives no meaning for the format parameter, so the description carries it: all seven enum-like values (webm, mp4-hevc, prores, gif, gif-low, lottie, aep) are explained with container, codec, transparency, target environment, and default. The illustration_id origin (illustrations[].id) is also restated from 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?

Opens with a specific verb+resource ('Get an animated illustration as a video, a GIF, or a Lottie animation') and immediately scopes it to illustrations whose media_types include 'animated', which separates it from the static get_illustration_png_url/get_illustration_svg siblings. The contrast with the search_illustrations preview links further pins down what this tool uniquely produces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use and when-not-to-use: 'ONLY for an illustration whose media_types includes "animated" - check a search_illustrations result first', and 'Reach for the search links while choosing, and for this tool once the choice is made.' It also tells the agent not to probe formats one by one and explains that a single refusal enumerates the available formats.

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 cover readOnly/openWorld; the description adds substantive behavior: the URL is presigned and expires in one hour, 'hd' requires a plan that covers the illustration, 'hd' counts against the paid-download limit, and refusals carry retry_after_seconds. It also warns that pixel dimensions vary and must be read from the response rather than assumed. This is well beyond what the annotations disclose.

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 and the sibling preference, then layers size, lifetime, args and returns in scannable blocks. The Args/Returns sections are compact and every sentence carries operational information 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?

Complete for a read-only URL-minting tool: it covers access gating, expiry, quota/retry behavior, and the return shape (url/width/height/expires_in_seconds or error). Only the 'ctx' arg is left at a general gloss, which is standard MCP plumbing.

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 only 50% (size has no schema description), and the description compensates fully: it enumerates the three size values, marks 'standard' as default, and explains the access tier that gates 'hd' plus its quota impact. illustration_id's provenance is restated consistently with 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 ('Get a PNG URL for an illustration') and immediately positions it against the sibling get_illustration_svg with the qualifier 'use when SVG is not available to you'. An agent can distinguish it from get_icon_png_url and the SVG variants 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?

Gives explicit when-to-use ('when SVG is not available to you'), names the preferred alternative ('SVG is preferred where you can get it - use get_illustration_svg'), and routes the persistence use case to 'preview.url' in a search result. Nothing is 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?

Goes well beyond the readOnlyHint/openWorldHint annotations: returns a presigned URL that expires in one hour, must be downloaded not stored, requires an account whose plan covers illustrations, counts toward a paid-download limit, and refusals carry retry_after_seconds. Rich behavioral context an agent needs before calling.

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 purpose and recommendation, then behaviors, then args/returns. Well organized and mostly earning its place, though the Returns block partly duplicates the output schema.

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, yet the description still frames the return shape and the refusal path usefully. Combined with the expiry and account constraints, an agent has everything needed to call it correctly.

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%, so the schema already documents illustration_id fully. The description restates the same guidance (id from search_illustrations results, illustrations[].id) without adding format or validation detail beyond the schema. 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 (get) and resource (illustration SVG link) and explicitly positions itself as the preferred format against the PNG sibling. An agent can distinguish it from get_illustration_png_url without opening either 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 explicit guidance: use this instead of PNG when possible, note the account/plan requirement for paid illustrations versus free_distribution: true needing no account, and route to preview.url for a permanent link. Names the alternative and the condition that selects it.

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 little beyond that: the 'Returns' note duplicates the existing output schema, and the defaults duplicate the schema. It does not mention ordering, item counts, or pagination edge cases.

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 one-line purpose followed by short Args/Returns sections; easy to scan. The 'ctx' line is unnecessary since it is not a user-facing parameter, but overall the text is tight.

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 read-only paginated list with an output schema present, the description covers purpose and pagination semantics. Nothing critical is missing, though it could have noted sibling alternatives.

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 0%, so the description carries the param burden and does so adequately: it explains that 'limit' caps results (default 10) and 'page' selects the page (default 1). It also mentions a 'ctx' argument that is not in the schema, which is slightly noisy but harmless.

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 all available icon categories'), which is clearly distinct from the illustration and search siblings. It does not, however, explicitly contrast itself with the other list_* tools (platforms, illustration categories/styles).

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 tool versus list_illustrations_categories, list_platforms, or search_icons. An agent must infer the context from the name alone.

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, and the description adds useful behavior beyond that: default page size, 1-based paging, and the notable semantic shift when parent_id is set (the single result is that category with children nested rather than listed at top level). Return shape is also 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?

Front-loaded with the purpose, then the category concept, then the routing hint, then Args/Returns. Efficient overall, though the Returns block is partly redundant with the existing output schema and the 'ctx: MCP context' arg line is boilerplate.

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, three-parameter, no-required-args listing tool with an output schema, the description covers purpose, argument meaning, pagination, and the parent_id nesting quirk. An agent has everything needed to call it correctly.

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 carries the full burden, and it does: limit is top-level categories per page (default 10), page is 1-based (default 1), and parent_id is an optional category pretty_id that narrows the result. Every argument gains meaning the schema alone does not provide.

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 illustration categories) and defines what a category is: a subject like animal or business with subcategories. It is clear on its own, but it does not contrast itself with the adjacent sibling list_categories, which an agent could easily confuse with this one.

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 downstream context: pass a category's pretty_id to search_illustrations to narrow a broad search word, and explains that parent_id narrows to a category. This routes usage well, but there are no explicit exclusions or comparisons against list_categories / list_illustrations_styles.

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 read-only/non-open-world safety profile, but the description adds behavioral context the annotations cannot: free_only's licensing semantics (paid account needed, and explicitly that a lack of the flag is not a bar for a subscriber) and the counterintuitive nature of the animated flag with measured examples (3d-business 19/1497, node 0 yet flagged). This is the kind of non-obvious behavior that prevents misuse.

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 purpose before mechanics, and the Args/Returns structure is scannable. It is longer than needed in places – the animated explanation restates 'property of the style, not a count' twice and adds a folksy icon-platform analogy – but the verbosity is mostly load-bearing given 0% schema coverage.

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, yet the description still sketches the return shape ({total, styles} with pretty_id, title, illustrations_count, free_distribution, animated) so the agent knows exactly which field feeds the next call. For a paged, filtered list tool with four undocumented params, nothing needed 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 0%, so the description carries the full burden and does: limit (styles per page, default 50), page (1-based, default 1), free_only (distribution licensing meaning), and animated (a property of the style, not a count, with the distinction mapped to media_types). All four undocumented parameters are given meaning beyond their names and types.

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 ('List all available illustration styles') and immediately explains the resource's role in the workflow (family consistency, pretty_id passed to search_illustrations). An agent can distinguish it from list_illustrations_categories and list_platforms 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?

Names the downstream consumer explicitly ('pass its pretty_id to search_illustrations for every illustration in a project') and provides an explicit when/when-not routing rule: use this tool to browse styles, but use search_illustrations(animated=True) to find illustrations that actually move. That is a concrete alternative selection rule, not an implication.

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. Beyond that the description contributes nothing behavioral — no rate limits, no note on whether the full set is always returned, no pagination semantics beyond the raw argument list. It neither contradicts nor enriches the annotations.

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?

Purpose is front-loaded in a single sentence, followed by a compact Args/Returns block. Minor waste exists in the 'ctx: MCP context for API access' line and in restating the return as 'List of icon platforms/styles' right after saying it lists them, but overall it is tight.

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 read-only listing tool with an output schema (so return shape need not be spelled out) and fully described parameters, the definition covers what an agent needs to invoke it correctly. The remaining gap is sibling disambiguation, which is a usage-guideline concern rather than a completeness failure.

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 carry the parameters, and it does: it explains 'limit' as maximum results (default 100) and 'page' as the pagination page (default 1). This compensates for the undocumented schema fields, though it adds no edge-case meaning (e.g., max limit, behavior past the last page).

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 all available icon platforms/styles'), so an agent can tell it is a listing/read tool. However, it does not differentiate itself from sibling list tools such as list_categories or list_illustrations_styles, and the name ('platforms') versus title ('icon styles') creates mild ambiguity about what is actually enumerated.

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 prerequisites, and no mention of when a caller should prefer this over search_icons or the other list_* siblings. The only implicit signal is 'all available', which is a scope statement rather than usage direction.

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?

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses the ~1-in-50 animation rarity, that animated results carry credential-free animation.gif/apng links needing no further call, that they must not be upscaled, and that the response is either {icons:[...]} or {error}. That is exactly the operational detail 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 and readable, but the six SEARCH TIPS bullets are largely paraphrases of each other ('simple, descriptive terms', 'action words', 'object names', 'synonyms', 'conceptually', 'single words'), so several sentences don't earn their place. Claiming to be 'the ONLY source for genuine Icons8 icons' adds no decision-relevant 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?

For a six-parameter search tool with an output schema, it covers everything an agent needs: query formulation, all filters, pagination, the interlock with the get_icon_* siblings via icon_id, and the error return. Nothing required 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 0%, so the description carries the whole burden and does: platform and category get example values ('ios', 'fluent', 'color'; 'transport', 'business'), offset is explained as pagination, amount as a maximum/cap, and animated gets non-obvious tri-state semantics (True/False/default) plus the note that about one icon in fifty is animated.

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 ('Search for icons') and scopes the source ('using the Icons8 API'), and the Returns section routes to the correct sibling tools (get_icon_svg, get_icon_png_url, get_icon_animation). It never distinguishes itself from the parallel search_illustrations sibling, so an agent choosing between icon and illustration search gets no explicit help.

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 usage context via the SEARCH TIPS block and names follow-up tools when more data is needed ('call get_icon_animation if you need the number'). There is no when-not-to-use guidance and no routing to search_illustrations or list_categories/list_platforms for browsing instead of searching.

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 give only readOnlyHint=true and openWorldHint=false; the description adds substantial non-structured behavior: preview URLs are permanent/no-second-call, animation previews are fixed 368x368, webm/mov are flat opaque #F7F7F7 with no alpha while poster is transparent, watermark state is exposed via animation.watermarked, and preview links are explicitly not for shipping. This is exactly the kind of behavioral disclosure the dimension rewards.

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?

Purpose and the sibling routing are well front-loaded, but the body is bloated and repeats the 'previews are for choosing, not shipping' theme at least twice, and restates the animation-block caveat in both the prose and the Args section. Most sentences carry real information, yet the ALL-CAPS warnings and duplicated rationale push length past what the task 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?

An output schema exists so return values need not be explained, yet the description still adds the field-level contract an agent needs (id feeds get_illustration_svg/png_url/animation, animation.lottie gates whether a Lottie call is worthwhile, free_distribution is not a licence judgement). For a 7-parameter search tool with heavy downstream tool chaining, nothing an agent needs to call 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 0%, so the description carries the full burden and does: it documents query (max 150 chars), style/category (pretty_ids from the list tools), free_only (licensing meaning), animated (with the caveat that some animated results lack the block), amount (default 10, max 100) and page (1-based, pagination-by-page not offset). It also adds search-strategy semantics (describe scenes not symbols, category narrows broad words).

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 ('Search Icons8 illustrations') and immediately distinguishes the resource from its closest sibling by defining illustrations as 'full scenes with people, objects and backgrounds' versus icons as 'a small symbol'. An agent can route between search_illustrations and search_icons without opening either 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?

Explicit when-to-use triggers (hero image, empty state, onboarding step, spot illustration) with an explicit counter-case ('for a small symbol in a button, a menu or a table, use search_icons instead'). It further names the supporting tools for parameter values (list_illustrations_styles, list_illustrations_categories) and when to escalate to get_illustration_animation.

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