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

With no annotations, the description carries the full burden: "Lista ao vivo" correctly signals a live, read-only listing operation, and pagination is mentioned so the agent knows results are paged. It stops short of stating that nothing is mutated, whether results are cached/real-time, what a returned post contains, or any rate/auth constraints.

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 purpose/ordering/filtering before the enum glossary, and no filler. The trailing enumeration of feed values is compact and functional, though the one-word entries at the end are terse enough to border on schema 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 6-parameter, no-annotation, no-output-schema tool, the description covers what is listed, how it is ordered, how it is filtered, and that it paginates. It leaves out the return payload shape and any operational caveats, which an agent would need to chain calls to godly_get or godly_media reliably.

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 second sentence does real work the schema cannot: it explains that "x" means design posts mined from X and "websites" means sites recorded as video (classic Godly), and it maps the sort values to recent/popular/staff picks. Tag and category are mentioned as filters, but their slug distinction is left mostly to 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?

"Lista ao vivo um feed do Godly/Recent Design" names a clear verb (list) and resource (feed), and the parenthetical enumerates the three orderings, so the agent knows exactly what data comes back. It never names godly_search or godly_get, so the browse-vs-search boundary is left implicit rather than stated.

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 implied: this is the tool to hit when you want an ordered, paginated feed filtered by tag/category, which is implicitly different from searching. However, there is no explicit "use this instead of X when…" statement, no exclusions, and no guidance on when a feed browse versus a taxonomy lookup (godly_taxonomy) is appropriate.

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 behavioral burden. It does useful work by disclosing the shape of the response (palette with hex + screen percentage, media types, conditional tool/skill fields), which substitutes for the missing output schema, but it never states that the operation is read-only, what happens on a bad id/slug, or whether anything is fetched remotely.

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 payload enumeration and ending with the accepted input forms. Dense but every clause adds information; the parenthetical tag categories are slightly list-heavy yet still earn their 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 no output schema and no annotations, the description steps in by enumerating returned fields and the accepted identifier formats, which is most of what an agent needs for a single-parameter lookup. Remaining gaps are failure behavior and sibling routing, both minor for a read-only detail fetch.

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 single parameter has 0% schema description coverage, so the description must compensate, and it does: it spells out that 'target' accepts a recent.design/i/... URL, a legacy godly URL, a 7-letter id, or a slug. That is genuinely additive meaning the bare string schema lacks, though no format precedence or validation rules are given.

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 ('Detalhes completos de um item') and then enumerates exactly what those details contain: description, creator, original link, tags by type, extracted palette, media list, and for tools/skills price, links and install command. An agent knows precisely what comes back. It does not name which sibling to use instead (e.g. godly_media for media-only), so it stops short of 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?

Usage is implied rather than stated: the enumerated payload makes clear this is the call for full detail on one known item, and the accepted input formats imply the item must already be identified. There is no explicit 'use this when X, use godly_media/godly_search when Y' routing against the five siblings.

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 load and does well: it discloses that files are downloaded, that frames extraction requires ffmpeg (an external dependency), that nothing is persisted by default, and that save=true writes to ~/godly-media/<id>. It omits what happens when ffmpeg is absent or how large responses/images are handled.

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 motion variant, then the persistence rule. Every clause conveys a distinct operational fact, though the mix of Portuguese prose with English keywords is slightly dense.

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 5-parameter tool with no annotations and no output schema, the description covers the mechanic, side effects, and external dependency well. The remaining gap is failure behavior (missing ffmpeg, items with no media), which is minor but would matter for an agent.

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 3 is the baseline, but the description adds real meaning: frames > 0 implies downloading the video and sampling N spread-out frames with ffmpeg, and save=true implies writing stills/videos/frames to ~/godly-media/<id>. This goes beyond the schema's terse field descriptions.

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: downloads the still (video poster or image) for each media of an item and returns it as an image, plus a frames mode for video. An agent can tell this is a visual-reference fetcher, distinct from godly_get's data retrieval, though the description never names the sibling it replaces.

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 conditional rule for the frames mode ('Pra motion, peça frames > 0') and implies the default still-only path, but says nothing about when to choose this tool over godly_get or godly_browse, nor what to do when an item has no media.

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 at all, the description carries the full behavioral burden, and it does disclose a genuine trait beyond structured data: the first call builds a local index (a few seconds) and subsequent calls are instant. It does not cover permissions, rate limits, or what the result objects contain. Useful latency disclosure, but the safety and output profile remain undocumented.

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 purpose, then content types, then match fields, then examples, then the index-latency note. Dense but each sentence contributes information. Slight redundancy between the content-type list and the schema's feed enum, but not wasteful enough to penalize further.

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 6-parameter search tool with no output schema and no annotations, the description does most of the necessary work: scope, matched fields, filter examples, and first-call cost. Missing pieces are the return shape (how results are ordered/paged) and the explicit boundary against godly_browse, which keeps it from a 5.

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 83%, so the baseline is 3, but the description adds real meaning: it says matching happens against título, descrição, criador and tags, which explains what the required query actually searches. It also adds the retrieval tip that English terms perform better, a non-obvious semantic not present in 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 and resource ("Busca referências de design no Godly / Recent Design") and enumerates the covered content types (interfaces, microinterações, motion, branding, OG images, ícones, app screens). It also names the fields matched (título, descrição, criador, tags). It does not differentiate itself from siblings like godly_browse or godly_taxonomy, so an agent must infer the boundary.

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?

Implied usage is clear from the content-type list and the query examples ('dark portfolio 3d', 'onboarding microinteraction'), and it hints that English terms retrieve better. There is no explicit when-to-use vs godly_browse/godly_get guidance and no statement of exclusions, so the choice among siblings 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?

No annotations are provided, so the description carries the full burden. It does disclose a real side effect — that refresh=true rebuilds the local index — which is genuinely useful behavioral context. However, it omits whether the rebuild is expensive or blocking, whether it needs permissions, and what the check result looks like beyond the three enumerated items.

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, zero filler: the first front-loads what is checked, the second explains the one parameter that changes behavior. Nothing is redundant or buried.

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 one-optional-parameter diagnostic tool with no output schema, the description covers what is checked and the one mutating option, which is enough to call it correctly. Minor gap: it never indicates the shape of the returned status (e.g., per-check pass/fail), which an agent may need to interpret results.

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, and it does: it explains that 'refresh=true' rebuilds the index, giving the boolean a concrete meaning beyond type and default. It does not spell out the false/default behavior explicitly, so the addition is good but not exhaustive.

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 ('Checa') and enumerates three concrete resources checked: the Recent Design API's responsiveness, the local index state, and whether ffmpeg is installed. This clearly identifies it as a diagnostic/health tool, implicitly distinguishing it from the data-oriented siblings (search, browse, get, taxonomy, media), though it never says so 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?

Usage is only implied: an agent can infer this is a pre-flight/diagnostic check, but the description never states when to call it (e.g., before search/browse operations, or when a sibling fails) or when not to. The only conditional guidance present concerns the parameter ('refresh=true reconstrói o índice'), not tool selection.

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 burden, and it does disclose the return content: categories with post counts and tags grouped by type. 'Lista' implies a non-mutating read, though it never says so outright, and there is no mention of caching or whether the tag list is exhaustive (the trailing '...' leaves that open).

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, with the downstream purpose at the end where it belongs. The open-ended 'component...' enumeration is the only soft spot, slightly blurring whether the listed types are complete.

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 single optional-parameter discovery tool with no output schema, the description adequately covers both what comes back and what to do with it. It leaves the feed-scoping behavior unexplained, which matters given the one parameter it accepts.

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 single 'feed' parameter is an enum with its own description, so the schema already does the work. The description adds no information about the feed filter, only about the tag-type grouping, so 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 ('Lista as categorias ... e as tags') plus the exact shape of the payload (categories with post counts, tags grouped by type). The named tag-type examples (color, style, interaction, framework, component) make it unmistakable against siblings like godly_search and godly_browse.

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 positions the tool as a precursor: the values returned are 'pra usar como filtro em godly_search e godly_browse'. That tells an agent when to call it instead of the search tools. It stops short of stating exclusions or prerequisites (e.g. whether the taxonomy is static or feed-dependent).

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