SkillFoxx

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

No annotations are provided, so the description carries the full disclosure burden. It does well on the return contract — listing install instructions, an install recipe with its status, access level with riskLevel/riskReasons, and an explicit caveat that risk is 'not a code quality rating' — but says nothing about failure behavior for a bad slug/section, response size, or language fallback, and the read-only nature is only implied by 'Read'.

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 intent is front-loaded with 'Read one catalog card', which is good, but the following sentence is a run-on that nests the risk-scale explanation mid-list ('what the tool adds to the agent, low minimal, medium extended, high broad'). The content earns its place; the packaging is dense to the point of being hard to parse in one pass.

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 explain return values and it largely does — install instructions, recipe plus status, risk fields with scale semantics, and limitations. The remaining gap is the undocumented lang parameter and silent behavior on unknown section/slug, which matters for a two-required-param lookup 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 description coverage is 0%, so the description must supply all parameter meaning. It fully enumerates the six valid section values, which compensates for the untyped string, but slug is only obliquely implied by 'one catalog card' and the lang parameter (ru/en, defaulting to ru) is never mentioned at all — leaving a third of 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 verb+resource pair is specific: 'Read one catalog card' with enumerated payload (install instructions, machine-readable install recipe, access level, limitations), and the section vocabulary (skills, mcp, cli, plugins, workflows, prompts) frames the domain. It differentiates from plan_install by routing step-by-step installs there, but says nothing about search_entries or list_categories, so the boundary with sibling retrieval tools is only partly drawn.

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 clear: this is the single-entry read, and one explicit alternative is named — call plan_install for step-by-step install in a specific agent. What is missing is the negative case: nothing tells the agent to prefer search_entries or list_categories when it does not already know a slug, which is the most likely misuse of this tool.

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 behavioral burden. It implies a read-only list operation and mentions card counts, but it does not state permissions, pagination, rate limits, or whether category names are localized. This is minimal behavioral context for a tool with no annotation coverage.

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 a single, front-loaded sentence with no wasted words. It is concise and easy to scan.

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 one-parameter listing tool, the description is adequate but incomplete. It explains what is returned at a high level, but omits what the lang parameter changes and provides no output shape details, which matters because there is no output schema.

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 should compensate for the undocumented lang parameter. It does not mention lang at all, leaving the agent to infer from the enum and default that it controls the language of category labels or counts. The schema exposes allowed values, but the description adds no semantic meaning.

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 catalog categories.' It also adds that results include card counts, which helps an agent understand the tool's output. It does not explicitly differentiate itself from siblings, but the purpose is still clear.

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 provides no explicit when-to-use guidance or alternatives. An agent can infer that this tool is for browsing categories, but there is no statement about when to choose it over search_entries or get_entry, nor any exclusions.

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 supplied, the description carries the full burden and does meaningful work: it discloses that secrets are never returned, only named placeholders, and it names the response fields including recipe status, access level, and reportToken. It stops short of stating permission/auth requirements or whether the call itself has any side effects, which leaves a gap for a zero-annotation tool.

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 the first clause, and the long agent list earns its space because the schema declares agent as a bare string with no enum. The prose is dense but not padded; the only mildly costly part is the alias enumeration, which could be tightened.

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?

There is no output schema, so the description properly describes what comes back, and it covers the two free-form string parameters that the schema leaves undocumented. The missing pieces are lang (which changes output language) and any statement of whether slug must come from a prior search — modest gaps for a four-parameter read 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 description coverage is 0%, so the description must compensate, and it partially does: it enumerates all valid agent values plus accepted site aliases, and lists the section values (skills, mcp, cli, plugins, workflows, prompts). However, slug is never explained beyond context, and lang (enum ru/en, default ru) is not mentioned at all — a real omission given the non-English default.

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 gives a specific verb and resource: 'Get exact install steps for one catalog tool in one agent', then enumerates exactly what is returned (commands, config path/snippet, one-click links, variables, recipe status, access level). It does not explicitly distinguish itself from get_entry or recommend_for_project, so sibling differentiation is left to inference.

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 establishes the usage context clearly: this is the step to run for a single tool in a single agent, and it names report_install as the required follow-up with the returned reportToken. What it does not say is when NOT to use it — e.g. whether get_entry should be called first to obtain the slug or to check availability.

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. It does disclose one genuinely useful behavioral constraint — never send source code or secrets, only a safe summary — but it says nothing about whether the call is read-only, whether it persists the project summary, or what the response shape 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 tight sentences with the purpose front-loaded and no filler. The privacy constraint is buried in the tail of the second sentence where it could be foregrounded, but nothing is wasted.

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 tool with no annotations, no output schema, and zero schema descriptions, the definition is only partly sufficient — it covers the main intent and payload but omits two parameters and any notion of the returned recommendation list. Adequate, not complete.

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 6 parameters, so the description must compensate. It explains goal, frameworks, dependencies and files (as "notable file names" rather than contents, a useful clarification), but leaves "problems" and "lang" entirely unexplained in both schema and description.

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?

"Recommend skills, MCP servers and CLI tools for a project" names a specific verb and enumerates the exact resources returned, so an agent knows what it gets back. It does not explicitly contrast itself with siblings like search_entries or plan_install, which is the only thing keeping it from a 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?

The description implies the usage context (project-scoped recommendation from a summary) and gives input guidance on what to send, but never states when to choose this over search_entries or get_entry, nor any exclusion beyond the privacy rule. Usage is inferable rather than prescribed.

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, this description carries the whole load, and it does disclose the privacy property (no personal data stored) plus the dependency on a token from plan_install. It leaves out failure and retry behavior, such as whether a repeated call double-counts the install or what happens if the token is stale. That omission keeps it below a 5.

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 sentences, front-loaded with the action and purpose, followed by the precondition and the exclusions. Every sentence carries necessary information and there is no padding.

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?

There is no output schema, and the description does not say what the call returns or how failures appear. It also leaves most of the required input contract, section/slug/agent/event, undefined, so an agent can follow the timing rules but cannot confidently build the payload from the description alone.

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 must explain the five parameters, but it only explains reportToken and where that value comes from. Nothing tells the agent what section, slug, agent, or the add/remove event enum mean, which is a real problem for the four required fields.

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: reporting to SkillFoxx that a catalog tool was installed, framed as keeping the anonymous install counter honest. It also ties itself to the plan_install sibling via reportToken, which helps separate it from search/list tools. It is clear but does not explicitly contrast with the other siblings, so it falls short of a 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?

Preconditions are explicit: call only after the user agreed and the installation finished without errors. Two exclusions are named with their reasons: npx skillfoxx installs (the CLI self-reports) and users who opted out of statistics. An agent knows exactly when to call and when not to.

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 supplied, the description carries the full behavioral burden. It does disclose one real behavioral fact beyond the schema: only published, reviewed cards are returned, implying a read-only, curated result set. However, it says nothing about matching semantics, ranking, empty-result behavior, or result volume, which matters for a search endpoint.

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 tight sentences with the purpose front-loaded and no filler. The result-scope note is appended efficiently. Slightly more could be said usefully, but nothing present is wasted.

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 search tool with three undocumented parameters, no annotations, and no output schema leaves the agent guessing at return shape (what fields a card has), pagination beyond 'limit', and the language behavior. The description covers intent but not enough of the operational surface.

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 three parameters, so the description must compensate and it does not. The required 'query' (2–120 chars), the 'limit' cap of 20, and especially 'lang' defaulting to 'ru' go entirely unexplained — an agent could easily search in the wrong language without noticing the default.

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 plus a concrete resource domain: search the SkillFoxx catalog of skills, MCP servers and CLI tools. An agent knows immediately what the tool fetches. It does not name or distinguish itself from siblings like get_entry or list_categories, so it stops short of a 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?

No when-to-use or when-not-to-use guidance is given. Nothing tells the agent to prefer search_entries over recommend_for_project or list_categories when it just needs to find an item. The 'published, reviewed only' clause is a result-scope statement, not routing guidance.

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