Illos illustrations

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses the data source (Illos.dev), the shape of each result (id, theme, size, free flag, page) and that free matches include a one-line install command. Remaining gaps—auth, rate limits, ranking behavior—are minor for a read-only search.

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 verb and resource, then usage, then return shape. The list of screen contexts is compact and every clause carries 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 compensates by enumerating the fields each result returns. Combined with 100% schema coverage on the four parameters and a clear read-only safety profile, 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 coverage is 100%, so the baseline is 3; the description adds real guidance by telling the agent to 'describe what the section explains' rather than pass keywords, which shapes how `need` should be phrased. It says nothing extra about limit, theme or free_only, but those are self-documenting.

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 with provenance: 'Find animated SVG illustrations from Illos.dev for a website or app.' Differentiation from get_illustration is only implicit (the note that results carry each match's id suggests a separate fetch-by-id tool), so it falls short of explicitly naming siblings.

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

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

Gives concrete when-to-use triggers: hero, feature section, empty state, docs page, onboarding, status screen. It also names what it replaces (stock art, emoji, empty space), but never says when NOT to use it or routes the agent to get_illustration/list_themes.

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

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

Beyond readOnlyHint/openWorldHint, the description discloses the free vs Pro return split (a Pro illustration only gives its page and how to obtain it, not embeddable assets) and the licensing terms for free illustrations. That is genuinely useful context an agent could not get from the schema, though it leaves the include_svg-on-Pro behavior unstated.

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 leads with the resource and then lists the three return pieces; little waste. The trailing free/Pro sentence is slightly compressed but still 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 simple two-parameter read tool with no output schema, the description covers outputs, licensing, and the free/Pro divergence well. The one gap is what happens to include_svg when the illustration is Pro-gated.

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 both parameters are documented there, including the size range for include_svg, so the description only needs to add value. It adds a little by implying SVG assets apply to free illustrations only, but nothing beyond that.

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 resource (one Illos illustration's install details) and enumerates what is returned: shadcn install command, SVG file, and licence. It is clearly distinct from find_illustrations, though it never names the sibling explicitly and frames itself as 'How to add' rather than 'Get install details'.

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 caller needs an id from find_illustrations (which appears in the schema, not the description) and the free/Pro branch hints at two outcomes. There is no explicit 'use this when you have an id and need to install' statement or exclusion against 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds that the set is fixed at four themes and spans free and Pro tiers, which implies a small, complete, non-paginated listing, but it says nothing about ordering or filtering.

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: the returned content first, the intended use second. No filler, no repetition of the tool name, nothing that could be trimmed.

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 must convey what comes back, and it names the three data points per theme plus tier availability. It is nearly complete, only omitting shape details such as whether counts are split per tier.

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 there is nothing to disambiguate and the baseline of 4 applies. The description correctly implies the call needs no input by framing the result as a fixed set of four themes.

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 resource (the four Illos themes) and precisely what is returned about each: appearance, illustration count, and free/Pro availability. It is clearly distinct from the illustration-fetching siblings, though it does not name them 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?

The sentence 'Use it to pick one theme for a site' gives a concrete selection context. There are no explicit exclusions or named alternatives, but for a zero-parameter catalog listing the intended moment of use is clear enough.

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